© 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. 12-GEMMASCOPE-RES-16K
    11. 2568
    Prev
    Next
    INDEX
    Explanations

    instances of personal pronouns and their variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Administrativna
    -0.89
    ロウィン
    -0.77
     Италијани
    -0.76
     CURIAM
    -0.75
    niſſe
    -0.74
     lenker
    -0.74
     zwiſchen
    -0.72
    <unused68>
    -0.72
    <unused41>
    -0.72
    <unused8>
    -0.72
    POSITIVE LOGITS
    -
    0.46
    The
    0.46
    _
    0.38
     
    0.35
    In
    0.35
    0
    0.33
    (
    0.32
    For
    0.31
    There
    0.31
     will
    0.30
    Activations Density 1.344%

    No Known Activations