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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3000
    Prev
    Next
    INDEX
    Explanations

    references to data structures and operations in programming contexts

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

    Code accessing values/entries of data structures

    np_acts-logits-general · gemini-2.0-flash

    map entries and collections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    addCriterion
    -0.91
     Савезне
    -0.85
    dafx
    -0.81
    IVEREF
    -0.81
     gynhyrchwyd
    -0.81
    protoimpl
    -0.81
    IsMutable
    -0.80
     doubtnut
    -0.80
     ModelExpression
    -0.75
    BeginContext
    -0.75
    POSITIVE LOGITS
    values
    0.59
     values
    0.56
    keys
    0.54
    .
    0.53
    Values
    0.45
     keys
    0.45
     lit
    0.43
    ps
    0.43
     solde
    0.42
    iter
    0.42
    Activations Density 0.077%

    No Known Activations