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. 2-GEMMASCOPE-RES-16K
    6. 3741
    Prev
    Next
    INDEX
    Explanations

    references to the matplotlib plotting library

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    labus
    -0.53
     ला
    -0.50
    Pup
    -0.48
    endpush
    -0.48
    زال
    -0.45
     waard
    -0.45
    DDG
    -0.45
     povezave
    -0.45
    INCREF
    -0.45
    jena
    -0.45
    POSITIVE LOGITS
    dispatch
    0.92
    Dispatch
    0.80
     dispatch
    0.78
    mailto
    0.76
    <caption>
    0.76
     }}"></
    0.71
     Relaciones
    0.69
     createContext
    0.67
     SwitchCompat
    0.66
    ionage
    0.65
    Activations Density 0.016%

    No Known Activations