© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 7730
    Prev
    Next
    INDEX
    Explanations

    terms related to legal fees and billing practices

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

    Legal/financial firms, billing, and partners

    np_acts-logits-general · gemini-2.0-flash

    law firms and partners

    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
    laş
    -0.29
     الك
    -0.28
     пос
    -0.27
     X
    -0.27
    leton
    -0.27
    la
    -0.26
    low
    -0.26
    getResponse
    -0.25
    czes
    -0.25
    ゙
    -0.25
    POSITIVE LOGITS
    twimg
    0.82
     $_"
    0.66
     raiſ
    0.63
     itſelf
    0.63
     deſt
    0.60
    MethodManager
    0.60
     témoig
    0.59
     ſur
    0.59
    niſſe
    0.59
    majánló
    0.57
    Activations Density 0.327%

    No Known Activations