© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 15851
    Prev
    Next
    INDEX
    Explanations

    symbols and terminology related to mathematical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ConstraintMaker
    -0.83
     Daß
    -0.72
     }}$}
    -0.71
     Exacts
    -0.69
     jsPsych
    -0.66
     myſelf
    -0.65
     magasiner
    -0.64
    afficheront
    -0.64
    :^
    -0.64
     poffe
    -0.63
    POSITIVE LOGITS
     ModelExpression
    0.59
     AssemblyCulture
    0.55
    Datuak
    0.53
     lutte
    0.48
    rna
    0.47
     mergeFrom
    0.46
     uska
    0.46
    WithIOException
    0.46
    oliber
    0.45
    thâu
    0.45
    Activations Density 2.102%

    No Known Activations