© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 105554
    Prev
    Next
    INDEX
    Explanations

    patterns or identifiers related to unique content or submissions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     surla
    -0.54
    genodigd
    -0.54
     gynhyrchwyd
    -0.50
    ########.
    -0.47
    esercito
    -0.46
     mû
    -0.44
     cuantas
    -0.44
    Portale
    -0.43
    hiculo
    -0.43
    Herzlich
    -0.43
    POSITIVE LOGITS
     poveznice
    0.42
    IBOutlet
    0.38
    ServletException
    0.38
    Jegyzetek
    0.36
    clearTimeout
    0.35
    LayoutStyle
    0.35
     disambiguazione
    0.35
    ViewImports
    0.34
    FACT
    0.32
     Италијани
    0.32
    Activations Density 0.003%

    No Known Activations