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. 7461
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the existence or quantity of something

    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
     neuem
    -0.67
    compos
    -0.63
    amounts
    -0.60
    ngOnInit
    -0.58
    Cuál
    -0.56
    σία
    -0.56
    мышлен
    -0.56
    zieży
    -0.54
    Something
    -0.54
     coś
    -0.54
    POSITIVE LOGITS
     few
    1.10
     many
    1.09
    MANY
    1.06
     MANY
    1.04
     Fewer
    1.01
     fewer
    1.00
    many
    0.98
     numerous
    0.96
     fewest
    0.94
    WithMany
    0.92
    Activations Density 0.109%

    No Known Activations