© 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. 2598
    Prev
    Next
    INDEX
    Explanations

    technical terms and symbols commonly used in scientific and mathematical contexts

    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
    MM
    -0.80
     CM
    -0.73
     KM
    -0.70
     MM
    -0.70
    KM
    -0.69
    pM
    -0.67
    mm
    -0.65
     UM
    -0.65
    ms
    -0.63
    mi
    -0.62
    POSITIVE LOGITS
     مرئيه
    0.91
    transQ
    0.69
    Maximum
    0.67
     AssemblyTitle
    0.66
    oredCriteria
    0.66
     Mention
    0.65
    Mention
    0.63
    maximum
    0.63
     modernity
    0.62
     maximum
    0.61
    Activations Density 0.550%

    No Known Activations