© 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. 10-GEMMASCOPE-RES-16K
    6. 4769
    Prev
    Next
    INDEX
    Explanations

    terminologies related to advanced mathematical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.70
     ujednoznacz
    -0.52
    providedIn
    -0.49
    发表于
    -0.45
     őket
    -0.44
    dymyr
    -0.42
     előtt
    -0.42
     potuto
    -0.42
     trå
    -0.40
    rawtypes
    -0.40
    POSITIVE LOGITS
    AccessorTable
    0.87
    AddTagHelper
    0.82
    setVerticalGroup
    0.76
    TagMode
    0.74
    windowFixed
    0.74
    tagHelperRunner
    0.74
    =?";
    0.69
     canlynol
    0.67
    ArgsConstructor
    0.64
    NUMX
    0.63
    Activations Density 1.791%

    No Known Activations