© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 11736
    Prev
    Next
    INDEX
    Explanations

    genetic terms and sequences related to mutations and genotyping techniques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arkiv
    -0.37
    Digi
    -0.36
    ejs
    -0.35
     gestes
    -0.35
     Dijk
    -0.34
     ля
    -0.34
    köy
    -0.32
     juges
    -0.32
     Paddy
    -0.32
     Digi
    -0.32
    POSITIVE LOGITS
    styleType
    0.66
    Jeografia
    0.65
    aarrggbb
    0.64
     bases
    0.63
    sizeCache
    0.62
     aden
    0.62
    ftagPool
    0.61
    嘧
    0.60
     base
    0.59
    OGND
    0.59
    Activations Density 0.742%

    No Known Activations