© 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. 23-GEMMASCOPE-RES-16K
    6. 8789
    Prev
    Next
    INDEX
    Explanations

    elements related to research methodology and data organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     few
    -0.56
     everywhere
    -0.54
    OuterClass
    -0.53
     TAMBIÉN
    -0.52
    writeFieldEnd
    -0.51
    reportWebVitals
    -0.50
    之类的
    -0.50
    的一切
    -0.50
    glicher
    -0.49
    few
    -0.49
    POSITIVE LOGITS
     apiece
    1.29
     each
    1.14
     namely
    1.12
    分别是
    1.12
     totaling
    1.05
     totalling
    1.01
    each
    1.00
     ciascuno
    0.94
    分别
    0.94
    namely
    0.93
    Activations Density 0.811%

    No Known Activations