© 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. 31-GEMMASCOPE-RES-16K
    11. 9618
    Prev
    Next
    INDEX
    Explanations

    specific numeric data and statistical analyses related to research studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    section heading numbers and decimal points in academic paper formatting.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    istoitu
    -0.65
    Зноскі
    -0.59
    Наводи
    -0.48
    хьтан
    -0.43
    лтамалар
    -0.37
    angio
    -0.36
    RefNanny
    -0.36
    ⎪
    -0.36
    vatore
    -0.36
    gink
    -0.35
    POSITIVE LOGITS
     '\\;'
    0.68
    bootstrapcdn
    0.65
    IntoConstraints
    0.56
    
    0.51
    setVerticalGroup
    0.51
     propOrder
    0.50
    tangentMode
    0.49
    ſelves
    0.49
    ValueStyle
    0.49
    Kde
    0.49
    Activations Density 0.133%

    No Known Activations