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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 14847
    Prev
    Next
    INDEX
    Explanations

    Java class definitions and related properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     symbolized
    -0.45
    ждый
    -0.45
    rakech
    -0.44
    bleau
    -0.43
    AFX
    -0.43
    typeparam
    -0.43
    CLUYE
    -0.43
     recognized
    -0.42
    aryng
    -0.42
    场上
    -0.41
    POSITIVE LOGITS
    Double
    1.01
     String
    1.00
     double
    0.99
     int
    0.99
     Double
    0.95
    double
    0.93
    String
    0.93
    int
    0.89
    Float
    0.89
     float
    0.86
    Activations Density 0.052%

    No Known Activations