© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 104577
    Prev
    Next
    INDEX
    Explanations

    terms related to processes, classifications, and states in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    webElementXpaths
    -0.66
    LookAnd
    -0.63
    IUrlHelper
    -0.60
     ویکی‌پدی
    -0.59
    Brainz
    -0.50
    ExtendWith
    -0.50
    AddTagHelper
    -0.50
    期刊论文
    -0.48
    httphttps
    -0.48
     ReactDOM
    -0.48
    POSITIVE LOGITS
    antaranya
    0.38
     življen
    0.36
     fornecer
    0.36
    Personendaten
    0.35
    ctrica
    0.35
     oferec
    0.35
     oferecer
    0.34
    ystema
    0.34
    utebol
    0.33
     Mezz
    0.33
    Activations Density 0.093%

    No Known Activations