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-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 9421
    Prev
    Next
    INDEX
    Explanations

    symbols and markup commonly used in coding and web formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    httphttps
    -0.85
    UnitTesting
    -0.79
    pyplot
    -0.78
     iArr
    -0.75
    ibi
    -0.69
    Lähteet
    -0.67
    DoubleQuotes
    -0.67
    ή
    -0.67
     axios
    -0.66
     FontWeight
    -0.65
    POSITIVE LOGITS
    «<
    1.59
    )<
    1.35
    ?<
    1.34
    :<
    1.34
    }<
    1.34
    /<
    1.33
     $<
    1.32
    .<
    1.32
    ;<
    1.31
    |<
    1.31
    Activations Density 0.260%

    No Known Activations