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-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3349
    Prev
    Next
    INDEX
    Explanations

    references to legal cases and court documentation related to Vermont

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

    Vermont, VT, Stowe, or Rutland

    np_acts-logits-general · gemini-2.0-flash

    Vermont and Vt

    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
     <>",
    -0.51
     CreateTagHelper
    -0.50
    ConstraintMaker
    -0.49
     oprot
    -0.49
     ModelExpression
    -0.48
     GenerationType
    -0.48
     صوتيه
    -0.48
     محفوظة
    -0.47
    awtextra
    -0.46
    localctx
    -0.46
    POSITIVE LOGITS
     Vermont
    0.92
    Vermont
    0.91
     Vt
    0.67
    pelier
    0.55
     VT
    0.53
     Bhutan
    0.51
     Burlington
    0.49
    Vt
    0.47
     Stowe
    0.47
     Rutland
    0.46
    Activations Density 0.236%

    No Known Activations