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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 478
    Prev
    Next
    INDEX
    Explanations

    pronouns and indicative references to subjects within text

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

    masculine pronouns (specifically "He").

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    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
     autorytatywna
    -0.81
     المعيارى
    -0.73
    ChildScrollView
    -0.72
     ProtoMessage
    -0.69
    featureID
    -0.69
    征詢我
    -0.69
     ddelwed
    -0.66
    aarrggbb
    -0.65
     незавершена
    -0.65
    ulemon
    -0.65
    POSITIVE LOGITS
    The
    0.53
    In
    0.48
    Is
    0.45
    It
    0.41
     bowiem
    0.41
    épa
    0.40
     In
    0.38
     The
    0.38
    hæng
    0.38
     therefore
    0.38
    Activations Density 0.277%

    No Known Activations