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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 6809
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to warranties and contracts

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

    "fitness" or "assignments" tokens

    np_acts-logits-general · gemini-2.0-flash

    warranty of fitness claim

    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
    скус
    -0.40
     honor
    -0.40
     Bro
    -0.37
     and
    -0.37
     Honorable
    -0.37
     Bran
    -0.37
     Oral
    -0.36
    IDENTIFIER
    -0.35
     I
    -0.35
     Honor
    -0.35
    POSITIVE LOGITS
     autorytatywna
    0.88
     disambiguazione
    0.83
    ValueStyle
    0.81
     transfieras
    0.80
    
    0.79
     pinulongan
    0.71
    الحياه
    0.71
    RenderAtEndOf
    0.71
     مرئيه
    0.69
     beginnetje
    0.69
    Activations Density 1.012%

    No Known Activations