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. 8285
    Prev
    Next
    INDEX
    Explanations

    phrases and terms that relate to performance metrics and evaluations

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

    high performance

    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
     Normdatei
    -0.49
    GEBURTSDATUM
    -0.47
    AutoField
    -0.44
    endphp
    -0.43
    atguigu
    -0.42
    EDEFAULT
    -0.41
    جوايز
    -0.40
     tag
    -0.40
     Steg
    -0.39
    StackNavigator
    -0.39
    POSITIVE LOGITS
     performance
    1.12
    performance
    1.02
    Performance
    1.01
     Performance
    0.99
     performances
    0.94
     PERFORMANCE
    0.93
     desempenho
    0.93
    PERFORMANCE
    0.92
     Performances
    0.83
     prestazioni
    0.81
    Activations Density 0.016%

    No Known Activations