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-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 16066
    Prev
    Next
    INDEX
    Explanations

    details about financial charges and fees associated with transactions

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

    fees or charges

    np_acts-logits-general · gemini-2.0-flash

    fees and charges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Portail
    -0.40
    itinéraire
    -0.30
    fromnode
    -0.30
    PCell
    -0.30
     jsPsych
    -0.29
     NSCoder
    -0.29
    ylem
    -0.28
     pinulongan
    -0.28
    VYMaps
    -0.28
    째
    -0.27
    POSITIVE LOGITS
     fees
    1.61
     fee
    1.46
     Fees
    1.41
    Fees
    1.32
    fees
    1.27
     Fee
    1.25
     charges
    1.20
     FEES
    1.18
    Fee
    1.16
    fee
    1.15
    Activations Density 0.167%

    No Known Activations