© 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-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 13134
    Prev
    Next
    INDEX
    Explanations

    references to tokens and their management in API interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ujednoznacz
    -0.58
    cshtml
    -0.41
     wires
    -0.39
     Billi
    -0.36
     billiard
    -0.34
     Einbau
    -0.34
    ToShow
    -0.33
     Draht
    -0.33
     Einsch
    -0.32
    awtextra
    -0.32
    POSITIVE LOGITS
     token
    2.81
     Token
    2.53
    token
    2.44
    Token
    2.31
     tokens
    2.25
     TOKEN
    2.11
     Tokens
    2.06
    TOKEN
    1.94
     getToken
    1.80
    tokens
    1.79
    Activations Density 0.209%

    No Known Activations