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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9834
    Prev
    Next
    INDEX
    Explanations

    terms related to session and token management in web applications

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

    Code snippets or authorization methods

    np_acts-logits-general · gemini-2.0-flash

    bearer token and jwt claims

    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
    ABAD
    -0.57
    ingway
    -0.49
    lognese
    -0.48
     Ghar
    -0.46
     filing
    -0.46
    EOUS
    -0.45
    enskap
    -0.45
     ligar
    -0.45
    abang
    -0.44
    PULL
    -0.44
    POSITIVE LOGITS
    jsonwebtoken
    0.96
    jwt
    0.85
     JWT
    0.84
     jwt
    0.82
    windowFixed
    0.78
    Claims
    0.78
     Jwt
    0.77
    claims
    0.76
    Jwt
    0.74
    JWT
    0.74
    Activations Density 0.094%

    No Known Activations