© 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-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 14521
    Prev
    Next
    INDEX
    Explanations

    terms related to fetching data or resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/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.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rekli
    -0.85
     Milner
    -0.78
    CardContent
    -0.71
     Club
    -0.68
    достатки
    -0.68
    PAN
    -0.68
    TypeDef
    -0.65
     club
    -0.65
     друзьями
    -0.65
    اليا
    -0.65
    POSITIVE LOGITS
     fetch
    1.61
     Fetch
    1.60
    fetch
    1.58
     FETCH
    1.57
    FetchType
    1.44
    Fetch
    1.37
    FETCH
    1.32
     fetched
    1.25
     fetching
    1.21
    Fetcher
    1.17
    Activations Density 0.083%

    No Known Activations