© 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. 24-GEMMASCOPE-RES-16K
    11. 7724
    Prev
    Next
    INDEX
    Explanations

    coding constructs related to variable declarations and loops

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

    Code blocks containing "for" or "foreach" loops

    np_acts-logits-general · gemini-2.0-flash

    for loops

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     שוליים
    -0.41
     }{@
    -0.39
    labelledby
    -0.39
    SPATH
    -0.39
    toggler
    -0.39
    HasColumnType
    -0.37
     suger
    -0.37
    ptid
    -0.37
    weds
    -0.36
    ragon
    -0.36
    POSITIVE LOGITS
     للمعارف
    0.62
    
    0.50
     estekak
    0.49
    richTextPanel
    0.47
    ChildScrollView
    0.46
    DebuggerNonUser
    0.44
    WriteBarrier
    0.44
     gezicht
    0.43
    enterOuterAlt
    0.42
    ędziesz
    0.41
    Activations Density 0.110%

    No Known Activations