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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 23-GEMMASCOPE-RES-16K
    6. 6329
    Prev
    Next
    INDEX
    Explanations

    data pertaining to demographics and medical conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enderror
    -0.49
     ujednoznacz
    -0.47
    providedIn
    -0.47
    RegistryLite
    -0.46
    modelBuilder
    -0.45
     pourriez
    -0.44
    าศ
    -0.43
    cloudfront
    -0.43
    osgi
    -0.43
    Похо
    -0.43
    POSITIVE LOGITS
     accounted
    1.97
     account
    1.96
     accounts
    1.91
    account
    1.71
     Account
    1.71
     accounting
    1.70
     ACCOUNT
    1.68
     constitute
    1.66
     Accounts
    1.60
    accounts
    1.58
    Activations Density 0.679%

    No Known Activations