© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 2798
    Prev
    Next
    INDEX
    Explanations

    references to cookies and methods for handling them in JavaScript

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

    "cookie" or "cookies"

    np_acts-logits-general · gemini-2.0-flash

    web cookie management

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setVerticalGroup
    -0.52
     Fall
    -0.49
    تقاوى
    -0.46
    Fall
    -0.45
    WriteLiteral
    -0.43
    Aspects
    -0.42
    PreAuthorize
    -0.42
    fall
    -0.42
    LogManager
    -0.41
     Main
    -0.41
    POSITIVE LOGITS
    Cookie
    1.13
     COOKIE
    1.08
    COOKIE
    1.06
     Cookie
    1.05
     cookie
    1.02
    cookie
    1.01
    Cookies
    0.97
     COOKIES
    0.94
     Cookies
    0.93
     cookies
    0.92
    Activations Density 0.107%

    No Known Activations