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-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3220
    Prev
    Next
    INDEX
    Explanations

    occurrences of law firms, corporate entities, and legal terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Appearing before "&" or "Co"

    np_acts-logits-general · gemini-2.0-flash

    company names with "&"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalColumn
    -0.76
    TestingModule
    -0.73
    IntoConstraints
    -0.73
    yntaxException
    -0.70
     propOrder
    -0.69
    WebElementEntity
    -0.69
    TemporalType
    -0.67
    httphttps
    -0.66
    
    -0.66
     AssemblyVersion
    -0.64
    POSITIVE LOGITS
     Brothers
    0.45
     Sons
    0.42
     firm
    0.39
     Bros
    0.39
    Brothers
    0.34
     company
    0.33
     prod
    0.33
     brothers
    0.33
     fu
    0.32
     firmas
    0.32
    Activations Density 0.540%

    No Known Activations