© 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. 18-GEMMASCOPE-RES-16K
    11. 3924
    Prev
    Next
    INDEX
    Explanations

    code and syntax related to HTTP headers and media types

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    HTTP headers or content type

    np_acts-logits-general · gemini-2.0-flash

    header and content type

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StoryboardSegue
    -0.78
    __':
    -0.65
    __":
    -0.60
    __((
    -0.58
    DeleteBehavior
    -0.55
    TypedDataSet
    -0.53
    Fns
    -0.53
    mvvm
    -0.53
    ^(@)
    -0.52
    Дере
    -0.52
    POSITIVE LOGITS
     header
    0.80
     headers
    0.76
    header
    0.76
    Header
    0.76
    Content
    0.72
     HEAD
    0.70
    headers
    0.70
    头
    0.70
    Headers
    0.69
     Content
    0.69
    Activations Density 0.557%

    No Known Activations