© 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-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 9787
    Prev
    Next
    INDEX
    Explanations

    references to guidance or advice related to problem-solving or decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    igshid
    -0.58
     '\\;'
    -0.58
    hésitez
    -0.54
    Quo
    -0.53
    pecially
    -0.53
     <=",
    -0.52
    ratulations
    -0.52
    ]$}
    -0.51
    asInstanceOf
    -0.51
    ContentAsync
    -0.50
    POSITIVE LOGITS
    μός
    0.92
     itſelf
    0.89
     himſelf
    0.74
    PullParser
    0.74
     Профиль
    0.74
     europeo
    0.73
    ſelf
    0.71
     Jefus
    0.71
    //
    0.67
     doubtnut
    0.66
    Activations Density 0.293%

    No Known Activations