Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 53012
    Prev
    Next
    INDEX
    Explanations

    programming language constructs related to variable assignments and function definitions

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

    boolean `covered`

    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
    Vidite
    -0.66
     createState
    -0.64
    PreferredItem
    -0.61
    posedge
    -0.59
    xaml
    -0.58
    migrationBuilder
    -0.58
     correctes
    -0.57
     '\\;'
    -0.57
    avyzd
    -0.57
    onActivityResult
    -0.57
    POSITIVE LOGITS
     afstand
    0.65
     distinction
    0.65
     nature
    0.63
     natureza
    0.63
    RectangleBorder
    0.62
    vedať
    0.62
     setIs
    0.58
     distancia
    0.58
     distância
    0.56
     naturaleza
    0.56
    Activations Density 0.092%

    No Known Activations