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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 6013
    Prev
    Next
    INDEX
    Explanations

    repetitive punctuation patterns in code

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

    Code, paths, filenames, or usernames

    np_acts-logits-general · gemini-2.0-flash

    code file paths

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.75
    GEBURTSDATUM
    -0.69
    awtextra
    -0.63
    twimg
    -0.60
    setVerticalGroup
    -0.58
     '{@
    -0.57
    fjspx
    -0.57
     الحره
    -0.57
    OGND
    -0.56
    ftagPool
    -0.55
    POSITIVE LOGITS
     Without
    0.42
    洛克
    0.39
     './
    0.39
     Cla
    0.39
     without
    0.39
     want
    0.39
     AssemblyVersion
    0.38
    ┤
    0.37
     Pras
    0.36
    Без
    0.36
    Activations Density 0.222%

    No Known Activations