© 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. 25-GEMMASCOPE-RES-16K
    6. 10511
    Prev
    Next
    INDEX
    Explanations

    terms related to low-cost or low-impact trends and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     StyleSheet
    -0.61
    fmt
    -0.55
    ">*</
    -0.52
    ParallelGroup
    -0.52
    anzia
    -0.51
     وتسجيلات
    -0.51
    forName
    -0.50
    djangoproject
    -0.50
     Whom
    -0.49
    uelo
    -0.49
    POSITIVE LOGITS
    key
    0.71
     (<
    0.70
     hanging
    0.66
    down
    0.65
    cost
    0.64
     key
    0.63
    hanging
    0.63
    ndes
    0.62
     Hanging
    0.62
    rider
    0.62
    Activations Density 0.243%

    No Known Activations