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. 20-GEMMASCOPE-RES-131K
    6. 46138
    Prev
    Next
    INDEX
    Explanations

    concepts related to classification and ranking systems

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

    ranking and categorization

    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
    __':
    
    -0.49
     שוליים
    -0.48
    jsxFileName
    -0.46
    copia
    -0.44
    addContainerGap
    -0.44
     متعلقه
    -0.43
    Біографія
    -0.43
    Copia
    -0.43
    __':
    -0.42
    allowNull
    -0.40
    POSITIVE LOGITS
     rankings
    0.71
     ranking
    0.67
     categorization
    0.63
     classification
    0.63
     categor
    0.62
    ranking
    0.61
     classifications
    0.60
    Rankings
    0.59
     grading
    0.59
     Rankings
    0.58
    Activations Density 0.072%

    No Known Activations