© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 4672
    Prev
    Next
    INDEX
    Explanations

    references to emotional or traumatic experiences and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases involving temporal or numerical references (years, time periods, dates).

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    temporal and discourse cues that set context or sequence events in explanatory or narrative text.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    temporal references to past events or time periods, particularly phrases indicating recollection or retrospection.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Photocase
    -0.46
    featureID
    -0.40
     Superan
    -0.39
    FormState
    -0.38
     lizenzfreie
    -0.36
     nakalista
    -0.36
     OMITBAD
    -0.36
    лтемелер
    -0.35
    afficheront
    -0.35
    miyorum
    -0.35
    POSITIVE LOGITS
     recently
    0.55
    +#+
    0.51
    recently
    0.50
     otomatig
    0.47
    Autoritní
    0.46
    anter
    0.46
     مُعرِّف
    0.45
     esempi
    0.44
     recent
    0.44
    uker
    0.43
    Activations Density 0.391%

    No Known Activations