© 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-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 1257
    Prev
    Next
    INDEX
    Explanations

    instances of the word "request" and its variations, indicating a focus on HTTP request handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    üli
    -0.59
    끗
    -0.56
    لكتر
    -0.55
    ناع
    -0.54
     aperçu
    -0.54
     thọ
    -0.51
    SpringBoot
    -0.51
    GIVEREF
    -0.51
     carré
    -0.50
    Nazionale
    -0.50
    POSITIVE LOGITS
    getRequest
    1.03
    Request
    0.93
    request
    0.89
     getRequest
    0.88
     Request
    0.84
     request
    0.81
    ServletRequest
    0.78
     HttpRequest
    0.77
    XtraEditors
    0.76
    WebRequest
    0.72
    Activations Density 0.032%

    No Known Activations