© 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. 22-GEMMASCOPE-RES-16K
    6. 10104
    Prev
    Next
    INDEX
    Explanations

    references to HTTP methods and AJAX requests

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

    HTTP request methods (PUT, GET, POST, Patch)

    np_acts-logits-general · gemini-2.0-flash

    http request methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IUrlHelper
    -0.53
    uxxxx
    -0.49
    AutoField
    -0.48
    PerPage
    -0.47
    xnn
    -0.47
    offsetof
    -0.47
    FunctionFlags
    -0.46
    ISupport
    -0.46
    DialogTitle
    -0.45
     rép
    -0.45
    POSITIVE LOGITS
     post
    1.21
    post
    1.14
     POST
    1.12
    POST
    1.11
     Post
    1.01
    Post
    1.01
    GET
    0.91
     GET
    0.90
     PUT
    0.82
     пост
    0.79
    Activations Density 0.096%

    No Known Activations