© 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. 4474
    Prev
    Next
    INDEX
    Explanations

    descriptions of study limitations and evaluations

    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
    addGap
    -0.70
    ThemeOverlay
    -0.63
    copyOf
    -0.63
    addPreferredGap
    -0.61
     Eighty
    -0.60
    Искәрмәләр
    -0.59
    ListItemIcon
    -0.58
    AsUp
    -0.58
     endfor
    -0.58
    GHIJKLM
    -0.57
    POSITIVE LOGITS
     three
    2.31
     two
    2.20
     four
    1.91
    three
    1.90
     several
    1.81
     trois
    1.77
    two
    1.77
     deux
    1.65
     drei
    1.61
     três
    1.59
    Activations Density 0.973%

    No Known Activations