© 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. 7-GEMMASCOPE-RES-16K
    11. 16010
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and terminology relevant to science

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.68
     Opus
    -0.62
    Opus
    -0.61
     poto
    -0.60
    usercontent
    -0.60
     AuthService
    -0.58
     disambiguazione
    -0.58
    QPalette
    -0.57
    GenerationType
    -0.57
     NDL
    -0.56
    POSITIVE LOGITS
     ugl
    0.43
    jillo
    0.43
    bootstrapcdn
    0.42
     horns
    0.40
     ugly
    0.40
     lucu
    0.40
     hideous
    0.40
     Pham
    0.40
     Cox
    0.36
     Elsie
    0.36
    Activations Density 2.031%

    No Known Activations