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. 2443
    Prev
    Next
    INDEX
    Explanations

    database connection and data manipulation keywords related to API 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
     betweenstory
    -0.98
    WebVitals
    -0.91
    SequentialGroup
    -0.82
    IntoConstraints
    -0.77
    Autoritní
    -0.73
    BufferException
    -0.72
     通販
    -0.72
    rawDesc
    -0.71
     cherchés
    -0.69
    ContentAsync
    -0.67
    POSITIVE LOGITS
    ]--;
    0.61
     useParams
    0.53
    .*")]
    0.51
     téléph
    0.50
     qualités
    0.46
     dipendenti
    0.44
     fratelli
    0.43
     laine
    0.43
     généraux
    0.43
     litio
    0.42
    Activations Density 0.993%

    No Known Activations