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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 3-GEMMASCOPE-RES-16K
    6. 12427
    Prev
    Next
    INDEX
    Explanations

    occurrences of special characters or formatting symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dafx
    -0.73
    basicConfig
    -0.73
    FunctionFlags
    -0.73
    Bibliograf
    -0.70
     חיצוניים
    -0.69
    CodedInputStream
    -0.69
    featureID
    -0.68
    makeConstraints
    -0.65
    lossary
    -0.64
    GOTREF
    -0.64
    POSITIVE LOGITS
     }}</
    0.46
    </s>
    0.41
    royd
    0.40
     Saltar
    0.40
    sin
    0.36
    мір
    0.35
     considérons
    0.35
    ?></
    0.34
     پہ
    0.34
    kN
    0.34
    Activations Density 0.567%

    No Known Activations