© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 5347
    Prev
    Next
    INDEX
    Explanations

    terms associated with mathematical settings or theorems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    synthesize
    -0.51
     lenker
    -0.47
     hari
    -0.47
     pa
    -0.47
    NSIndexPath
    -0.45
     Highways
    -0.45
    SPRING
    -0.45
     خلا
    -0.45
    JUST
    -0.44
     vari
    -0.43
    POSITIVE LOGITS
    ftagPool
    0.93
    endpush
    0.78
     Meksiku
    0.75
    Personensuche
    0.74
    الحياه
    0.73
    UnusedPrivate
    0.70
    省市镇
    0.69
     AssemblyTitle
    0.69
     mergeFrom
    0.67
    цездатний
    0.66
    Activations Density 1.827%

    No Known Activations