© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 16335
    Prev
    Next
    INDEX
    Explanations

    technical details related to measurements and physical properties in a scientific context

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

    attenuation, per hour, full damage

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     ***!
    -0.72
    bootstrapcdn
    -0.68
    expandindo
    -0.66
     defaultstate
    -0.66
    verifyException
    -0.66
    AndEndTag
    -0.65
     مرئيه
    -0.63
     invokingState
    -0.63
     betweenstory
    -0.60
    帖最后由
    -0.60
    POSITIVE LOGITS
     cumbre
    0.34
     Lauf
    0.29
     rate
    0.28
     judiciales
    0.27
     envejec
    0.27
    timer
    0.27
     Leistungen
    0.26
     Akhir
    0.26
     dignidad
    0.26
     Keuangan
    0.26
    Activations Density 0.186%

    No Known Activations