© 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. 223
    Prev
    Next
    INDEX
    Explanations

    terms related to advanced mathematical concepts in geometry and algebra

    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
     مرئيه
    -0.65
    Hentet
    -0.63
    awtextra
    -0.63
    AndEndTag
    -0.62
     HasFactory
    -0.57
     jadx
    -0.57
     _$
    -0.57
    tagHelperRunner
    -0.56
     Wikimedijinoj
    -0.56
     InputDecoration
    -0.54
    POSITIVE LOGITS
    /*
    0.60
     announced
    0.54
     conject
    0.54
     repro
    0.53
    announced
    0.53
    ituary
    0.51
     ANNOUNC
    0.51
     Beno
    0.51
    typeorm
    0.50
     Announced
    0.50
    Activations Density 2.428%

    No Known Activations