© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 6938
    Prev
    Next
    INDEX
    Explanations

    the word "token" and its variants in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cohé
    -0.88
     GLS
    -0.80
     screenWidth
    -0.76
     GridLayout
    -0.76
    (!__
    -0.75
     Shakspeare
    -0.74
     sánh
    -0.74
    Filmographie
    -0.73
     eyesight
    -0.72
     LoginComponent
    -0.72
    POSITIVE LOGITS
     token
    3.64
    token
    3.26
     Token
    3.19
     tokens
    3.15
    Token
    2.96
     Tokens
    2.69
    TOKEN
    2.64
     TOKEN
    2.63
    Tokens
    2.57
    tokens
    2.49
    Activations Density 0.033%

    No Known Activations