© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 1089
    Prev
    Next
    INDEX
    Explanations

    instances of attention-grabbing or captivating actions and experiences

    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
     pits
    -0.51
    Skocz
    -0.49
    !*\
    -0.49
    वरी
    -0.49
    CloseOperation
    -0.47
     surla
    -0.47
    HOUT
    -0.47
    {{/
    -0.46
     SIMBAD
    -0.46
    Портал
    -0.45
    POSITIVE LOGITS
     hold
    1.04
     glimpse
    0.97
    hold
    0.92
     glimpses
    0.82
     sight
    0.82
     attention
    0.81
     basah
    0.76
    phrases
    0.72
     onto
    0.72
    phrase
    0.71
    Activations Density 0.226%

    No Known Activations