© 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. 704
    Prev
    Next
    INDEX
    Explanations

    occurrences of opening and closing curly braces

    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
    مقاله
    -0.59
    oredCriteria
    -0.50
    edar
    -0.47
    enseignements
    -0.46
     ""));
    -0.46
     give
    -0.46
    fører
    -0.45
    ]();
    -0.44
     Hutchison
    -0.43
     expectations
    -0.43
    POSITIVE LOGITS
    tabular
    0.96
    CJK
    0.94
    enumi
    0.87
    enumii
    0.86
    array
    0.74
    tagHelperRunner
    0.73
     CreateTagHelper
    0.71
    MethodManager
    0.67
    EndInit
    0.63
    aligned
    0.63
    Activations Density 0.035%

    No Known Activations