© 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. 3-GEMMASCOPE-RES-16K
    11. 8378
    Prev
    Next
    INDEX
    Explanations

    expressions of happiness or positivity, often associated with smiles, alongside references to military or armed forces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     engaged
    -0.31
    Uwagi
    -0.28
     inquiry
    -0.28
     inquiries
    -0.27
     odds
    -0.27
     indag
    -0.27
     trouble
    -0.27
     Bader
    -0.26
    Remarque
    -0.26
    ]]);
    -0.25
    POSITIVE LOGITS
    setVerticalGroup
    0.86
     smile
    0.79
     AssemblyVersion
    0.74
    RTSN
    0.69
     rgb
    0.69
     vooz
    0.68
    __(/*!
    0.68
    MigrationBuilder
    0.68
    <unused16>
    0.67
     unknownFields
    0.67
    Activations Density 0.086%

    No Known Activations