© 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. 25-GEMMASCOPE-RES-16K
    11. 2646
    Prev
    Next
    INDEX
    Explanations

    the presence of mathematical or programming notation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #+#
    -0.50
    CompilerServices
    -0.49
     iyong
    -0.47
    tagHelperRunner
    -0.46
     into
    -0.44
     bakom
    -0.43
    ंत्री
    -0.42
    tagHelper
    -0.42
    horabuena
    -0.42
     Unless
    -0.42
    POSITIVE LOGITS
    зулта
    0.70
    ftagPool
    0.59
    исленность
    0.58
    rrggbb
    0.57
    QMetaType
    0.55
     =>
    0.55
    лтамалар
    0.55
     ziren
    0.54
    Spoljašnje
    0.54
    ineno
    0.54
    Activations Density 0.090%

    No Known Activations