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

    Neuronpedia

    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
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 5327
    Prev
    Next
    INDEX
    Explanations

    code structure and syntax related to programming functions and return values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.54
     defaultstate
    -0.49
     biotin
    -0.39
    setopt
    -0.39
     MotionEvent
    -0.39
    KommentareTeilen
    -0.39
    Gator
    -0.38
    ieteur
    -0.38
     Keep
    -0.37
    PullParser
    -0.37
    POSITIVE LOGITS
    ↵↵↵↵↵↵↵
    0.66
    ↵↵↵↵↵↵↵↵↵↵↵
    0.65
    ↵↵↵↵
    0.63
    ↵↵↵↵↵↵
    0.62
    ↵↵↵↵↵↵↵↵↵
    0.61
    ↵↵↵↵↵
    0.60
    ↵↵↵↵↵↵↵↵
    0.60
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.60
    ↵↵↵↵↵↵↵↵↵↵↵↵
    0.57
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.57
    Activations Density 0.222%

    No Known Activations