© 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. 58927
    Prev
    Next
    INDEX
    Explanations

    programming language syntax elements, particularly related to object definitions and static methods

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

    programming keywords and declarations

    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
     Roskov
    -0.67
    PreferredItem
    -0.62
    脚注の使い方
    -0.62
    +#+#
    -0.58
    principalColumn
    -0.58
    ftagPool
    -0.56
    adaptiveStyles
    -0.55
    󠁴
    -0.55
     ujednoznacz
    -0.54
     سكانية
    -0.54
    POSITIVE LOGITS
    IntOverflow
    0.32
     especially
    0.32
    
    0.31
     dermed
    0.30
     särskilt
    0.29
    ksanakan
    0.29
    ariConfig
    0.29
    skraft
    0.28
    orithmic
    0.28
     spes
    0.28
    Activations Density 0.079%

    No Known Activations