© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 10217
    Prev
    Next
    INDEX
    Explanations

    occurrences of self-referential language in the context of programming or classes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SqlSession
    -0.70
    enumi
    -0.60
    ̈́
    -0.56
     *
    
    
    -0.55
    ?
    
    -0.52
    …?
    -0.52
     extremism
    -0.52
    </blockquote>
    -0.52
    ...");
    
    -0.50
     Vergrößern
    -0.50
    POSITIVE LOGITS
     unknownFields
    0.75
    GEBURTSDATUM
    0.66
    oredCriteria
    0.63
    PostInfinity
    0.62
    LookAnd
    0.61
    tagHelperRunner
    0.59
    AutoScale
    0.58
    SourceChecksum
    0.58
    writeFieldEnd
    0.57
    OwnProperty
    0.56
    Activations Density 0.040%

    No Known Activations