© 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-2-2B
    7. Residual Stream - 16k
    9. 17-GEMMASCOPE-RES-16K
    11. 5715
    Prev
    Next
    INDEX
    Explanations

    code snippets related to dynamic class manipulation in a UI context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    KeySpec
    -0.68
    onViewCreated
    -0.67
    ">'+
    -0.63
    MemoryWarning
    -0.61
     Tapia
    -0.59
    저
    -0.59
    ⓧ
    -0.59
     propOrder
    -0.58
    ;">
    -0.58
    consulté
    -0.58
    POSITIVE LOGITS
    classnames
    0.61
    addClass
    0.55
     Fokus
    0.48
     saites
    0.48
    ervlak
    0.46
     FontWeight
    0.45
     оказыва
    0.45
    classname
    0.45
    BURGH
    0.44
    ίναι
    0.44
    Activations Density 0.109%

    No Known Activations