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
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 8489
    Prev
    Next
    INDEX
    Explanations

    references to code snippets, specifically those containing the backtick character

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    träger
    -0.41
    InjectAttribute
    -0.36
     exchange
    -0.36
    sprogramm
    -0.31
    Portale
    -0.30
     Energy
    -0.29
    exchange
    -0.29
     Allociné
    -0.29
     energy
    -0.29
    WIN
    -0.29
    POSITIVE LOGITS
     שוליים
    0.65
    :✨
    0.63
    textbf
    0.59
    Skocz
    0.58
    Vidite
    0.56
     Prudence
    0.55
    textit
    0.53
    aarrggbb
    0.53
    classnames
    0.51
     Italijanski
    0.51
    Activations Density 0.953%

    No Known Activations