© 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. 80467
    Prev
    Next
    INDEX
    Explanations

    occurrences of double underscores, typically used for special methods or attributes in programming

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

    double underscore names

    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
     تضيفلها
    -0.90
     defaultstate
    -0.85
    脚注の使い方
    -0.79
    bootstrapcdn
    -0.75
    postsleuth
    -0.74
    saraba
    -0.71
    findpost
    -0.69
    stdc
    -0.69
    WriteTagHelper
    -0.68
     فريبيس
    -0.67
    POSITIVE LOGITS
    __
    0.54
    sson
    0.47
     or
    0.43
    <>();
    0.43
     objectives
    0.42
    jenigen
    0.42
     those
    0.41
    ment
    0.41
    !
    0.40
    nement
    0.40
    Activations Density 0.018%

    No Known Activations