© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 94114
    Prev
    Next
    INDEX
    Explanations

    terms related to flushing and disposal processes

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    flushing and flushing out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    tagHelperRunner
    -0.76
     onCreateView
    -0.65
    styleType
    -0.61
     beginnetje
    -0.60
    ConstraintMaker
    -0.60
     OMITBAD
    -0.59
     المعيارى
    -0.57
    matism
    -0.57
    LookAnd
    -0.56
    AndEndTag
    -0.55
    POSITIVE LOGITS
     flushing
    1.19
     flushed
    1.13
     flush
    1.03
     Flush
    1.00
    Flush
    0.98
    flush
    0.94
     Flushing
    0.90
    FLUSH
    0.82
    fflush
    0.69
     rinsing
    0.65
    Activations Density 0.031%

    No Known Activations