© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13643
    Prev
    Next
    INDEX
    Explanations

    technical terms and code snippets related to programming and software development

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

    Markup, code, or license-related texts

    np_acts-logits-general · gemini-2.0-flash

    german terms

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    X
    -0.49
    S
    -0.47
    n
    -0.47
    h
    -0.46
    k
    -0.45
    ns
    -0.44
    g
    -0.44
    m
    -0.44
    x
    -0.44
    H
    -0.43
    POSITIVE LOGITS
    iſen
    0.79
    ſcher
    0.79
     ſind
    0.75
    iſten
    0.73
     queſta
    0.72
    ſchaft
    0.71
    ſehen
    0.71
    ſchen
    0.69
     FontWeight
    0.69
    ロウィン
    0.69
    Activations Density 0.128%

    No Known Activations