© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 10828
    Prev
    Next
    INDEX
    Explanations

    key components or elements related to organizational structure and hierarchy

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

    preceding "of" or related to components

    np_acts-logits-general · gemini-2.0-flash

    part or component of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nonUne
    -0.36
    Diweddarwch
    -0.34
    chossen
    -0.34
    visor
    -0.33
    +#+#
    -0.32
     esboço
    -0.31
    reiches
    -0.31
     Rer
    -0.31
     Jem
    -0.31
     сбо
    -0.31
    POSITIVE LOGITS
    featureID
    0.57
     мәкал
    0.56
     <<<<<<<<<<<<<<
    0.54
    onViewCreated
    0.54
     linkovi
    0.50
    DockStyle
    0.49
     mauva
    0.49
    IBarButtonItem
    0.49
     fédé
    0.48
     defStyleAttr
    0.48
    Activations Density 0.965%

    No Known Activations