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. 5-GEMMASCOPE-RES-16K
    6. 7541
    Prev
    Next
    INDEX
    Explanations

    words related to rescue or salvation themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CPtr
    -0.68
    WithMany
    -0.63
    Šaltiniai
    -0.62
     AspNetCore
    -0.59
    iddhar
    -0.53
    thalam
    -0.50
     Amic
    -0.50
     typelib
    -0.48
     Bourgoin
    -0.48
    ặ
    -0.48
    POSITIVE LOGITS
     rescue
    1.85
     Rescue
    1.71
     rescues
    1.70
     rescuing
    1.70
    rescue
    1.69
     rescued
    1.65
    Rescue
    1.62
     rescu
    1.44
     saved
    1.41
     Rettung
    1.33
    Activations Density 0.146%

    No Known Activations