© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 128082
    Prev
    Next
    INDEX
    Explanations

    language related to validation and predictability in scientific or experimental contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    RenderAtEndOf
    -0.66
     autorytatywna
    -0.65
     CreateTagHelper
    -0.60
    EndContext
    -0.59
    CppMethod
    -0.57
     مشين
    -0.56
    Autoritní
    -0.56
    saraba
    -0.51
    InSection
    -0.49
     AssemblyProduct
    -0.48
    POSITIVE LOGITS
     promised
    0.47
     promises
    0.43
     promise
    0.41
     confirmed
    0.40
    대로
    0.37
     confirmation
    0.37
     rzeczyw
    0.36
     expectations
    0.35
     Umsetzung
    0.35
     실
    0.34
    Activations Density 0.062%

    No Known Activations