© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 10553
    Prev
    Next
    INDEX
    Explanations

    terms related to token-based authentication and authorization processes

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

    Tokens or processes related to authorization/authentication

    np_acts-logits-general · gemini-2.0-flash

    jsonwebtoken and jwt tokens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 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
    FieldBuilder
    -0.36
    writeFieldEnd
    -0.35
    還是
    -0.33
     снима
    -0.32
    放下
    -0.31
    colnshire
    -0.31
     calories
    -0.31
     calorías
    -0.30
    还是
    -0.30
    Seznam
    -0.30
    POSITIVE LOGITS
    jsonwebtoken
    1.49
    jwt
    0.87
     Jwt
    0.80
     jwt
    0.71
     незавершена
    0.67
    webtoken
    0.65
     JWT
    0.65
    wts
    0.64
    Jwt
    0.64
    JWT
    0.59
    Activations Density 0.196%

    No Known Activations