© 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. 36-GEMMASCOPE-RES-16K
    11. 7751
    Prev
    Next
    INDEX
    Explanations

    elements related to asynchronous programming and API interaction in web development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hook
    -0.54
    mybatisplus
    -0.47
     useContext
    -0.47
     pandemic
    -0.47
    コロナ禍
    -0.44
    hook
    -0.44
     useState
    -0.43
     HOOK
    -0.43
     Omicron
    -0.42
    🥹
    -0.42
    POSITIVE LOGITS
    SequentialGroup
    0.79
    Gweler
    0.58
    PropTypes
    0.55
    Personendaten
    0.54
     PropTypes
    0.52
    componentWill
    0.50
    Tikang
    0.49
    WindowConstants
    0.49
    EndGlobalSection
    0.47
    nextProps
    0.47
    Activations Density 0.174%

    No Known Activations