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. 46104
    Prev
    Next
    INDEX
    Explanations

    references related to data analytics or data management systems

    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
    zkod
    -0.39
    )))),
    -0.37
    ("")]
    
    -0.37
    ″]
    -0.35
     Mün
    -0.35
    glGet
    -0.35
    "]),
    -0.34
     actual
    -0.33
    _]
    -0.33
     immun
    -0.31
    POSITIVE LOGITS
    ConverterFactory
    5.47
    IntoConstraints
    0.93
     Италијани
    0.86
    MessageTagHelper
    0.83
    Personensuche
    0.78
    LookAnd
    0.77
     CommonModule
    0.76
    AccessorTable
    0.74
     BrowserModule
    0.73
    AdapterFactory
    0.73
    Activations Density 0.000%

    No Known Activations