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. 9411
    Prev
    Next
    INDEX
    Explanations

    concepts related to phylogenetic analysis and molecular data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Phylogenetic tree analysis and calculations

    np_acts-logits-general · gemini-2.0-flash

    phylogenetic tree calculation and analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    reportWebVitals
    -0.56
    ApiModelProperty
    -0.55
     Vorsch
    -0.53
    interceptors
    -0.50
     кӀош
    -0.48
    andoah
    -0.47
    vyšší
    -0.47
    XDECREF
    -0.47
    setopt
    -0.46
    QP
    -0.46
    POSITIVE LOGITS
    Phylogenetic
    0.71
     phylogenetic
    0.68
     phylogeny
    0.66
     bootstrap
    0.64
     AssemblyVersion
    0.63
     saites
    0.63
     mt
    0.61
     phylog
    0.61
     समीक्षाओं
    0.60
    ########.
    0.59
    Activations Density 1.325%

    No Known Activations