Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 120185
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to weather data structures and control signals

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

    GoldenWaveDetail, KOFControl, EruptSignal

    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
    存于互联网档案馆
    -0.58
    rungsseite
    -0.52
     czego
    -0.50
    crum
    -0.46
     Uff
    -0.43
    󠁴
    -0.42
     erſt
    -0.42
     Denial
    -0.41
    Ӕ
    -0.41
    MOUTH
    -0.41
    POSITIVE LOGITS
    layui
    0.52
    Bakgrunnsstoff
    0.45
    zaine
    0.44
     springfox
    0.43
    wpdb
    0.42
    الدراسه
    0.42
    htbp
    0.40
    +#+
    0.39
     čer
    0.39
     Gaulle
    0.38
    Activations Density 0.026%

    No Known Activations