Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 11451
    Prev
    Next
    INDEX
    Explanations

    references to token management and related operations in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     विश्वसनीयता
    -0.59
     defaultstate
    -0.59
    ">//
    -0.58
    IInterface
    -0.57
    \{\\
    -0.56
    marshaller
    -0.55
     متعلقه
    -0.55
    BagLayout
    -0.55
    Aiheesta
    -0.55
    CloseOperation
    -0.55
    POSITIVE LOGITS
     token
    3.56
    token
    3.23
     Token
    3.01
    Token
    2.89
     TOKEN
    2.48
    TOKEN
    2.43
     tokens
    2.42
     Tokens
    2.14
    getToken
    2.08
     getToken
    2.00
    Activations Density 0.097%

    No Known Activations