© 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. 17-GEMMASCOPE-RES-16K
    6. 6876
    Prev
    Next
    INDEX
    Explanations

    Java programming constructs, particularly class definitions and access modifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "]["
    -0.49
    ({"
    -0.48
     int
    -0.47
    twimg
    -0.47
    otka
    -0.45
     pidana
    -0.44
    telli
    -0.44
    ()?.
    -0.43
    зами
    -0.43
     fit
    -0.42
    POSITIVE LOGITS
    rungsseite
    0.94
     linkovi
    0.85
     ExecuteAsync
    0.84
    Erreferentziak
    0.79
    endphp
    0.78
     snippetHide
    0.75
    tableFuture
    0.75
    Obrázky
    0.74
    脚注の使い方
    0.73
    
    0.72
    Activations Density 0.011%

    No Known Activations