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. 9832
    Prev
    Next
    INDEX
    Explanations

    Java exceptions and class declarations related to input/output operations

    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
     coat
    -0.56
    csv
    -0.53
     myö
    -0.53
    CSV
    -0.51
     sementes
    -0.51
    migrationBuilder
    -0.51
    towych
    -0.51
    曖昧さ回避
    -0.51
    astia
    -0.51
    Csv
    -0.50
    POSITIVE LOGITS
    IOException
    2.71
    SQLException
    1.11
    FileNotFound
    1.01
    JSONException
    0.94
     onAnimation
    0.88
    новништво
    0.82
    TargetException
    0.79
    RemoteException
    0.72
    abetes
    0.70
    ValueStyle
    0.69
    Activations Density 0.024%

    No Known Activations