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. 9862
    Prev
    Next
    INDEX
    Explanations

    references to biological sample collection and analysis procedures

    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
    rensa
    -0.57
    ercises
    -0.55
    terness
    -0.53
    DispatchToProps
    -0.51
    örté
    -0.51
    atase
    -0.51
    ädie
    -0.50
     Alfonso
    -0.50
    Kilder
    -0.48
    édia
    -0.48
    POSITIVE LOGITS
     samples
    1.29
     sample
    1.25
     Samples
    1.19
    sample
    1.15
    samples
    1.14
     échanti
    1.14
     SAMPLES
    1.10
     SAMPLE
    1.10
     Sample
    1.08
    Samples
    1.06
    Activations Density 1.167%

    No Known Activations