© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4487
    Prev
    Next
    INDEX
    Explanations

    coding-related keywords and attributes associated with user interface elements and data handling

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

    UI or code elements related to setting fields as read-only or disabled.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    󠁣
    -0.59
    Diweddarwch
    -0.53
     personlig
    -0.52
     corazones
    -0.51
    líben
    -0.50
     persönlich
    -0.50
     recomendada
    -0.50
     Wikimedijinoj
    -0.50
     estekak
    -0.50
     cielos
    -0.49
    POSITIVE LOGITS
    readonly
    0.61
     readonly
    0.56
    ReadOnly
    0.51
    MockBean
    0.51
    readOnly
    0.48
     harmless
    0.47
     dead
    0.46
     static
    0.46
     passive
    0.45
     inactive
    0.44
    Activations Density 0.270%

    No Known Activations