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. 20-GEMMASCOPE-RES-16K
    6. 13099
    Prev
    Next
    INDEX
    Explanations

    terms related to financial and accounting activities

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

    before ".com" or related to returns/history

    np_acts-logits-general · gemini-2.0-flash

    company returns or crash driver side

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     queſta
    -0.75
     utafitiHapana
    -0.74
     surla
    -0.70
     ExecuteAsync
    -0.69
     ſehr
    -0.69
     ſei
    -0.69
     témoig
    -0.68
    tvguidetime
    -0.67
     ſehen
    -0.66
    ɵɵ
    -0.66
    POSITIVE LOGITS
    ↵↵
    0.51
    ↵
    0.42
    ↵↵↵
    0.35
    )
    0.35
     =
    0.35
    ?
    0.34
    ardecer
    0.33
    impresa
    0.32
    ,
    0.32
     Verwaltung
    0.32
    Activations Density 0.829%

    No Known Activations