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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 10576
    Prev
    Next
    INDEX
    Explanations

    topics related to financial evaluations and stock performance

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

    following "part," "ward," or similar terms

    np_acts-logits-general · gemini-2.0-flash

    parteffectorresponse

    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
     Ky
    -0.35
    zarchiwizowane
    -0.34
    السكان
    -0.33
    Cyfeiriadau
    -0.31
     vot
    -0.30
     (!
    -0.28
     lampa
    -0.27
     banned
    -0.27
     monthly
    -0.26
     oly
    -0.26
    POSITIVE LOGITS
    SBATCH
    0.82
    
    0.77
     Infórmanos
    0.75
     kasarigan
    0.73
     Geſch
    0.70
     MessageBoxIcon
    0.67
     ujednoznacz
    0.66
     MainAxisSize
    0.63
    ropractic
    0.63
    abrigo
    0.63
    Activations Density 3.790%

    No Known Activations