© 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. 8-GEMMASCOPE-RES-16K
    6. 10159
    Prev
    Next
    INDEX
    Explanations

    indications of transient changes and fluctuations in states or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    critto
    -0.55
    …………………………………………
    -0.50
    ))/(
    -0.48
    inburgh
    -0.47
    icom
    -0.47
     Horowitz
    -0.46
    reportError
    -0.46
     gordura
    -0.46
     responsáveis
    -0.45
    laub
    -0.45
    POSITIVE LOGITS
    astify
    0.76
     fluctu
    0.76
     fluctuating
    0.72
    Geplaatst
    0.70
    NOPQRST
    0.69
     shifts
    0.69
     shifting
    0.67
    ValueStyle
    0.66
     Vary
    0.66
    TagMode
    0.65
    Activations Density 0.433%

    No Known Activations