© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 15430
    Prev
    Next
    INDEX
    Explanations

    options and features related to software updates and settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/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.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     and
    -0.33
     therefore
    -0.31
    :
    -0.31
     also
    -0.30
     however
    -0.30
    ,
    -0.30
     ones
    -0.30
     jej
    -0.30
     —
    -0.30
    ?
    -0.30
    POSITIVE LOGITS
    <unused14>
    0.86
    <unused79>
    0.85
    [@BOS@]
    0.85
    <unused3>
    0.85
    <unused52>
    0.85
    <unused28>
    0.85
    <unused51>
    0.85
    <unused41>
    0.85
    <unused8>
    0.85
    <unused16>
    0.85
    Activations Density 2.042%

    No Known Activations