© 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-2-9B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 4906
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate dominant participants or predominant characteristics in a study or data context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.78
     myſelf
    -0.73
     itſelf
    -0.69
     '\\;'
    -0.68
    iſchen
    -0.66
    niſſe
    -0.65
    adaptiveStyles
    -0.65
    MLLoader
    -0.63
    therosclerosis
    -0.63
     AssemblyCulture
    -0.63
    POSITIVE LOGITS
     mainly
    1.42
     Mainly
    1.31
     primarily
    1.30
     mostly
    1.28
    mainly
    1.27
     Mostly
    1.26
    Mainly
    1.25
    Mostly
    1.23
    mostly
    1.20
     chiefly
    1.17
    Activations Density 0.482%

    No Known Activations