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

    Neuronpedia

    Jacobian LensNEW
    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. 14847
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to scientific methods and diagnostics

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

    preceding non-English words

    np_acts-logits-general · gemini-2.0-flash

    technical and scientific terms

    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
     CreateTagHelper
    -0.82
    AndEndTag
    -0.71
    CppMethod
    -0.69
    principalColumn
    -0.69
     disambiguazione
    -0.66
    󠁴
    -0.65
    ronpa
    -0.61
    featureID
    -0.61
    WebElementEntity
    -0.60
    şört
    -0.59
    POSITIVE LOGITS
    czenia
    0.38
     wyn
    0.34
     esté
    0.34
     quedan
    0.33
     tampoco
    0.33
    reth
    0.31
    škai
    0.31
     digna
    0.30
     cómo
    0.30
    ubo
    0.30
    Activations Density 1.746%

    No Known Activations