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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 7547
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to mathematical structures, specifically in the context of statistical processes and probability theory

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.47
     kiệm
    -0.42
    XtraEditors
    -0.38
     beat
    -0.37
    queryInterface
    -0.37
     ControllerBase
    -0.35
    ndo
    -0.34
    urek
    -0.34
    yan
    -0.34
     ErrInvalid
    -0.33
    POSITIVE LOGITS
    =(
    1.26
     $(
    1.21
     }(
    1.13
    }=(
    1.10
     $(\
    1.09
     =(
    1.09
     tuple
    1.06
    ((
    1.02
    =(\
    1.02
     [(
    1.01
    Activations Density 0.851%

    No Known Activations