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. 3-GEMMASCOPE-RES-16K
    6. 6389
    Prev
    Next
    INDEX
    Explanations

    phrases related to capability and potential in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     transfected
    -0.55
     Baus
    -0.55
     uncanny
    -0.53
     auprès
    -0.53
    zzarella
    -0.52
     escrit
    -0.52
     Specifies
    -0.51
     PropertyChanged
    -0.50
    PropertyChanging
    -0.50
    Modific
    -0.50
    POSITIVE LOGITS
    évaluateur
    0.83
     getting
    0.74
    Autoritní
    0.74
    basicConfig
    0.71
    brainly
    0.71
     أجل
    0.69
     ће
    0.68
     pudesse
    0.68
    plotlib
    0.68
     avoiding
    0.67
    Activations Density 0.405%

    No Known Activations