© 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. 21-GEMMASCOPE-RES-16K
    6. 13351
    Prev
    Next
    INDEX
    Explanations

    legal terms and references related to court cases and scientific classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مرئيه
    -0.85
     disambiguazione
    -0.77
     الدولى
    -0.64
     AspNetCore
    -0.59
    onomous
    -0.56
     ویکی‌پدیای
    -0.56
     maneu
    -0.56
     समीक्षक
    -0.55
    GeneratedCode
    -0.55
    
    -0.54
    POSITIVE LOGITS
     dolore
    0.51
     consectetur
    0.51
     adipis
    0.49
     asper
    0.48
    melho
    0.46
    DebuggerNonUser
    0.46
    --}}
    0.46
    NoSuchAlgorithm
    0.45
    featureID
    0.44
     Mini
    0.44
    Activations Density 0.072%

    No Known Activations