© 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-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 27660
    Prev
    Next
    INDEX
    Explanations

    points or arguments being made in a discussion or text

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

    point of X or point is X

    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
     مشين
    -0.58
     SafeMath
    -0.56
    KommentareTeilen
    -0.54
     initComponents
    -0.54
    __*/
    -0.52
     HasFactory
    -0.52
    OGND
    -0.48
     defaultdict
    -0.46
    ModelSerializer
    -0.46
     وتسجيلات
    -0.46
    POSITIVE LOGITS
     point
    1.34
     POINT
    1.24
     Point
    1.20
    POINT
    1.11
    point
    1.08
     points
    1.05
    Point
    1.03
     Points
    0.97
    points
    0.94
     POINTS
    0.92
    Activations Density 0.113%

    No Known Activations