Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 13-GEMMASCOPE-RES-16K
    6. 12279
    Prev
    Next
    INDEX
    Explanations

    references to "band" and related concepts, particularly in contexts involving groups, organizations, or physical elastic materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pob
    -0.76
     Reinh
    -0.68
     Spez
    -0.67
    Scor
    -0.67
    jeh
    -0.67
    Lus
    -0.67
    Pants
    -0.66
    toPromise
    -0.66
    ühren
    -0.66
     Aless
    -0.66
    POSITIVE LOGITS
    CodeAttribute
    1.08
    BAND
    1.00
     BAND
    0.99
     незавершена
    0.98
     bands
    0.95
     AssemblyTitle
    0.92
     initComponents
    0.90
    Bands
    0.89
    NamedQueries
    0.86
     band
    0.85
    Activations Density 0.207%

    No Known Activations