© 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. 1-GEMMASCOPE-RES-16K
    6. 15140
    Prev
    Next
    INDEX
    Explanations

    instances of the word "dispatch" and variations of the word "bite."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AsUp
    -0.81
     BoxFit
    -0.64
    RuleContext
    -0.61
     дописавши
    -0.61
     Talley
    -0.61
    SharedDtor
    -0.60
    ArrowToggle
    -0.60
    UnknownFieldSet
    -0.60
     AspNetCore
    -0.59
    gnore
    -0.57
    POSITIVE LOGITS
    Tw
    1.09
     Tw
    1.07
    tw
    1.06
     tw
    1.03
     horizon
    0.95
    TL
    0.90
    ju
    0.88
     Sheriff
    0.86
     sheriff
    0.85
    tl
    0.85
    Activations Density 0.081%

    No Known Activations