© 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. 39-GEMMASCOPE-RES-16K
    11. 1655
    Prev
    Next
    INDEX
    Explanations

    phrases expressing personal beliefs and reflections about relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VolleyError
    -0.33
    私たちは
    -0.32
    anskje
    -0.32
    ngdoc
    -0.31
    rítica
    -0.31
    Iya
    -0.30
    ICIOS
    -0.29
    zeba
    -0.29
    Ios
    -0.28
     lenker
    -0.28
    POSITIVE LOGITS
     i
    3.23
    i
    1.75
     ive
    1.21
    ｉ
    1.18
     ii
    1.14
     im
    1.03
     iii
    0.91
    ⅰ
    0.90
     iv
    0.90
     і
    0.84
    Activations Density 2.642%

    No Known Activations