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. 14634
    Prev
    Next
    INDEX
    Explanations

    references to species and their classifications

    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
     صفحۀ
    -0.66
     BrowserModule
    -0.64
     المعيارى
    -0.61
     Tamp
    -0.60
     Comp
    -0.58
     HART
    -0.56
     Schot
    -0.56
     صوتيه
    -0.56
    devamını
    -0.55
    Bord
    -0.55
    POSITIVE LOGITS
    pecies
    0.59
    Species
    0.56
     species
    0.56
     Species
    0.54
    species
    0.54
     elseif
    0.51
    spesies
    0.51
     SPECIES
    0.49
     specie
    0.49
     MenuItem
    0.49
    Activations Density 0.328%

    No Known Activations