© 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 - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 8753
    Prev
    Next
    INDEX
    Explanations

    terms related to medical conditions and biological processes

    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
     Volks
    -0.47
    OutOf
    -0.47
    Volks
    -0.46
    onOptions
    -0.46
    Christoph
    -0.44
    QObject
    -0.44
     coj
    -0.43
     ronda
    -0.42
    Vicki
    -0.42
     parser
    -0.41
    POSITIVE LOGITS
    ore
    1.30
    ORE
    1.22
    ure
    1.12
    URE
    1.09
     Ware
    1.05
     Hare
    1.02
    IRE
    1.01
    ire
    1.01
    Ware
    1.00
    lore
    0.93
    Activations Density 0.898%

    No Known Activations