© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 11161
    Prev
    Next
    INDEX
    Explanations

    occurrences of conditional statements and specific keywords related to frequency or occurrence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     methodologies
    -0.48
     resourceCulture
    -0.45
    routine
    -0.45
     methodology
    -0.44
     Tunes
    -0.43
     routine
    -0.43
    談社
    -0.43
     Tailor
    -0.43
     Num
    -0.42
     inaugural
    -0.42
    POSITIVE LOGITS
     sometimes
    0.60
    sometimes
    0.58
     autorytatywna
    0.56
     kadang
    0.54
    RegressionTest
    0.52
     bitte
    0.52
     fometimes
    0.51
     parfois
    0.50
     HasFactory
    0.50
     manchmal
    0.49
    Activations Density 0.178%

    No Known Activations