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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9-GEMMASCOPE-RES-131K
    6. 68685
    Prev
    Next
    INDEX
    Explanations

    references to specific technical terms and concepts in programming and sports

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

    INCIDENTAL damages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -1.13
    
    -0.73
    脚注の使い方
    -0.61
    tagHelperRunner
    -0.58
    esModule
    -0.58
    complexContent
    -0.57
     oprot
    -0.54
    LookAnd
    -0.53
     convertView
    -0.51
     FetchType
    -0.50
    POSITIVE LOGITS
    only
    0.98
     only
    0.76
    Only
    0.74
    ONLY
    0.67
     Only
    0.67
     seulement
    0.64
     ONLY
    0.60
     uniquement
    0.59
     únicamente
    0.56
     только
    0.56
    Activations Density 0.001%

    No Known Activations