© 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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 73732
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to biology and medicine

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    saraba
    -0.41
     ſch
    -0.41
     juſ
    -0.39
    stdafx
    -0.39
     ſtate
    -0.37
     houſe
    -0.37
     ſche
    -0.37
    复制代码
    -0.36
     miſ
    -0.36
     समीक्षक
    -0.36
    POSITIVE LOGITS
     Meksiku
    0.56
     Baillargeon
    0.48
    LabelTagHelper
    0.46
     GenerationType
    0.45
    tonode
    0.42
    strptime
    0.42
    PerformLayout
    0.41
    permitAll
    0.41
    المناصب
    0.41
    הערות
    0.41
    Activations Density 0.143%

    No Known Activations