Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 11241
    Prev
    Next
    INDEX
    Explanations

    elements associated with mathematical symbols and equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    󠁴
    -0.56
     eksemp
    -0.56
    addContainerGap
    -0.53
    AndEndTag
    -0.52
    隅
    -0.50
     页
    -0.47
    kulum
    -0.46
    DateTimeField
    -0.46
    homonymie
    -0.45
     kommunen
    -0.45
    POSITIVE LOGITS
    mathbf
    0.96
    mathcal
    0.91
    mathbb
    0.86
    boldsymbol
    0.82
    mathscr
    0.68
    mathfrak
    0.65
    widetilde
    0.56
    WriteTagHelper
    0.55
    ۜ
    0.54
    operatorname
    0.53
    Activations Density 0.683%

    No Known Activations