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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 16121
    Prev
    Next
    INDEX
    Explanations

    terms related to variable access modifiers in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.66
    liceerd
    -0.63
     doubles
    -0.63
    myname
    -0.60
    TRAILING
    -0.58
    itudinal
    -0.57
    Expandable
    -0.57
    crollView
    -0.56
    ariConfig
    -0.56
     expires
    -0.55
    POSITIVE LOGITS
    private
    1.02
     private
    0.75
    public
    0.67
    MigrationBuilder
    0.62
     Private
    0.61
    ngdoc
    0.60
    moveToFirst
    0.59
     privato
    0.58
    modelBuilder
    0.56
    Private
    0.56
    Activations Density 0.013%

    No Known Activations