© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 58862
    Prev
    Next
    INDEX
    Explanations

    expressions of willingness to help or assist

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    happy to assist or help

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     geçir
    -0.42
     cathédrale
    -0.39
     near
    -0.35
     graduación
    -0.35
     oblasti
    -0.35
     prefeito
    -0.34
     gedrag
    -0.34
     maire
    -0.33
     the
    -0.33
    ]));
    -0.32
    POSITIVE LOGITS
     gladly
    0.69
    Willing
    0.65
    Gratis
    0.63
    glad
    0.63
    gratu
    0.61
    willing
    0.60
    omitempty
    0.59
    wong
    0.59
     accept
    0.58
     CURIAM
    0.58
    Activations Density 0.006%

    No Known Activations