© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 5531
    Prev
    Next
    INDEX
    Explanations

    codes or abbreviations related to file formats or codes used in programming

    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
     المعيارى
    -0.80
     autorytatywna
    -0.66
     ujednoznacz
    -0.64
     censiti
    -0.57
    richTextPanel
    -0.53
     queſta
    -0.50
     alluminio
    -0.50
     península
    -0.49
    onViewCreated
    -0.49
    PullParser
    -0.48
    POSITIVE LOGITS
    hand
    0.42
    log
    0.38
    ann
    0.36
    inger
    0.36
    wur
    0.35
    gal
    0.35
    pak
    0.35
    般
    0.34
    den
    0.34
    bre
    0.34
    Activations Density 3.247%

    No Known Activations