© 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. 12-GEMMASCOPE-RES-16K
    11. 15071
    Prev
    Next
    INDEX
    Explanations

    the presence of numerical data or mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    раздо
    -0.73
    ssymb
    -0.68
    omiast
    -0.66
    <%@
    -0.61
     Yag
    -0.61
    jähriger
    -0.59
    dymyr
    -0.58
    tocin
    -0.58
     McPherson
    -0.58
    gatsby
    -0.56
    POSITIVE LOGITS
     they
    0.87
     it
    0.84
     MainAxisSize
    0.83
     we
    0.80
    ftagPool
    0.77
     these
    0.74
     combien
    0.72
     you
    0.66
     the
    0.66
     this
    0.62
    Activations Density 0.081%

    No Known Activations