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. 0-GEMMASCOPE-RES-16K
    6. 326
    Prev
    Next
    INDEX
    Explanations

    instances of the word "some" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مشين
    -0.77
     Offisielt
    -0.77
     parlant
    -0.76
     internetowa
    -0.74
    Vlastnosti
    -0.73
    arraycopy
    -0.73
    IonicModule
    -0.71
    Портал
    -0.71
     geslacht
    -0.70
    Jegy
    -0.69
    POSITIVE LOGITS
    some
    1.44
     some
    1.13
    Some
    1.09
    som
    1.00
     som
    0.97
     Some
    0.95
    SOME
    0.93
    Som
    0.88
     SOME
    0.88
    SOM
    0.85
    Activations Density 0.164%

    No Known Activations