© 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. 10-GEMMASCOPE-RES-16K
    6. 15269
    Prev
    Next
    INDEX
    Explanations

    elements related to structured data processing and syntax in a coding or programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/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.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }());
    -0.53
    abetes
    -0.49
     decision
    -0.48
     pre
    -0.48
     group
    -0.48
     disponibilités
    -0.47
     most
    -0.47
    orsese
    -0.47
    Compre
    -0.47
     idea
    -0.47
    POSITIVE LOGITS
     tartalomajánló
    0.74
     виправивши
    0.73
    äksi
    0.69
     Majefty
    0.69
    OGND
    0.68
     Houſe
    0.68
     themſelves
    0.67
    bbene
    0.66
     figliu
    0.66
     MainAxisSize
    0.66
    Activations Density 0.356%

    No Known Activations