© 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. 13784
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of usage and guidelines for applying methods in various contexts

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

    how to use

    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
    makeText
    -0.49
     propOrder
    -0.49
    UrlResolution
    -0.47
    dafx
    -0.45
    IBOutlet
    -0.44
     saites
    -0.44
    IVEREF
    -0.43
    zellan
    -0.43
     disambiguazione
    -0.43
    quiel
    -0.43
    POSITIVE LOGITS
    使い方
    0.60
     Usage
    0.60
     usage
    0.59
    Usage
    0.57
     misuse
    0.51
     Penggunaan
    0.48
     usages
    0.46
    usage
    0.46
     utilization
    0.46
     misused
    0.43
    Activations Density 0.045%

    No Known Activations