© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 31390
    Prev
    Next
    INDEX
    Explanations

    elements related to interventions and strategies in education and social contexts

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

    related to describing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ".
    -0.91
    ”.
    -0.88
    .
    -0.84
    '.
    -0.82
    ’.
    -0.78
    .”
    -0.73
    ."
    -0.70
    ].
    -0.69
    ).
    -0.68
    "].
    -0.67
    POSITIVE LOGITS
     createSprite
    0.73
    ,:),
    0.71
     transférez
    0.71
    ³,
    0.68
     ועוד
    0.67
     الرياضيه
    0.66
    SerializedSize
    0.63
    ~,
    0.63
    ,:);
    0.62
    complexType
    0.62
    Activations Density 0.573%

    No Known Activations