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

    Neuronpedia

    Jacobian LensNEW
    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. 31-GEMMASCOPE-RES-16K
    11. 14893
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the occurrence of events after a specific time or condition

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

    the word "After" at the beginning of sentences or clauses introducing a temporal sequence or event.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ویکی‌پدیا
    -0.52
    今から
    -0.48
    Diweddarwch
    -0.46
    ungsbedingungen
    -0.46
    ništ
    -0.44
     '\\;'
    -0.44
    Autoritní
    -0.42
    حوالہ
    -0.41
    Datuak
    -0.41
     يتيمه
    -0.40
    POSITIVE LOGITS
     failed
    0.81
     unsuccessful
    0.76
     successful
    0.73
     successes
    0.68
     successfully
    0.68
    successful
    0.66
    failed
    0.64
    Successful
    0.63
     успешно
    0.63
     extensive
    0.63
    Activations Density 0.307%

    No Known Activations