© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 535
    Prev
    Next
    INDEX
    Explanations

    closing braces and parentheses in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/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.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.79
     EconPapers
    -0.69
    OGND
    -0.65
    ]--;
    -0.64
     AssemblyTitle
    -0.63
    ){}
    -0.62
     مشين
    -0.60
    )‏
    -0.60
    Erreferentziak
    -0.58
    AccessorTable
    -0.57
    POSITIVE LOGITS
     return
    2.55
    return
    2.48
     Return
    2.10
     returned
    2.01
     returning
    2.00
     returns
    1.95
     RETURN
    1.92
     Returning
    1.86
    Return
    1.79
     Returns
    1.69
    Activations Density 0.060%

    No Known Activations