© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 9919
    Prev
    Next
    INDEX
    Explanations

    elements related to authentication tokens and their usage in API requests

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

    code tokens

    np_acts-logits-general · gemini-2.0-flash

    token and related words

    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
     CURIAM
    -0.61
    CloseOperation
    -0.56
     manuscripts
    -0.55
    IInterface
    -0.55
     Wainwright
    -0.55
    ebvre
    -0.54
     Waray
    -0.54
     Nied
    -0.53
    Aiheesta
    -0.53
     disponibilités
    -0.53
    POSITIVE LOGITS
     token
    3.35
     Token
    3.02
    token
    3.02
    Token
    2.89
     TOKEN
    2.41
     tokens
    2.41
    TOKEN
    2.39
     Tokens
    2.23
    Tokens
    2.02
    getToken
    2.02
    Activations Density 0.078%

    No Known Activations