© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 4854
    Prev
    Next
    INDEX
    Explanations

    specific location names and associated activities

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

    Text after colons, parentheses, or brackets

    np_acts-logits-general · gemini-2.0-flash

    Whitey Bulger, Borneo, train

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumi
    -0.71
    Gambas
    -0.68
     Combien
    -0.58
    endfor
    -0.54
    rach
    -0.53
     Privy
    -0.52
    وحة
    -0.51
    ApiOperation
    -0.51
    出版年
    -0.51
     تحص
    -0.51
    POSITIVE LOGITS
    RenderAtEndOf
    0.73
     Br
    0.51
     للمعارف
    0.50
    íncia
    0.50
    IBOutlet
    0.49
    ญิง
    0.46
    Cau
    0.46
    DialogContent
    0.45
     colspan
    0.45
    liferay
    0.45
    Activations Density 0.068%

    No Known Activations