© 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. 6-GEMMASCOPE-RES-16K
    11. 6984
    Prev
    Next
    INDEX
    Explanations

    patterns related to the use of periods and segments in coding or text structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (
    -0.72
    <b>
    -0.69
    <strong>
    -0.61
    ,
    -0.59
    вига
    -0.57
    ậy
    -0.54
     
    -0.51
    DA
    -0.50
    wachung
    -0.50
     
    -0.50
    POSITIVE LOGITS
    __).
    1.30
     }}$.
    1.12
    ########.
    1.10
    +".
    1.10
    +'.
    1.08
    ="'.$
    1.03
    _'.$
    1.02
    ='.$
    1.02
    =".$
    1.00
    $.}
    0.98
    Activations Density 0.034%

    No Known Activations