© 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. 13289
    Prev
    Next
    INDEX
    Explanations

    ideas related to evaluation and consideration of consequences

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

    followed by hedges or qualifiers

    np_acts-logits-general · gemini-2.0-flash

    statements of fact or belief

    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
     للاسماء
    -0.73
     utafitiHapana
    -0.59
    脚注の使い方
    -0.58
    ConstraintMaker
    -0.56
     defaultstate
    -0.56
    CodedInputStream
    -0.54
    StoryboardSegue
    -0.54
    Izvori
    -0.52
    الدراسه
    -0.52
    yntaxException
    -0.52
    POSITIVE LOGITS
     nonetheless
    0.39
    /*
    0.36
     nevertheless
    0.33
    あげて
    0.30
     enough
    0.29
    toBeDefined
    0.29
    warnai
    0.27
     indruk
    0.27
    enough
    0.26
     hoofd
    0.26
    Activations Density 0.492%

    No Known Activations