© 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. 34-GEMMASCOPE-RES-16K
    6. 11329
    Prev
    Next
    INDEX
    Explanations

    references to numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SequentialGroup
    -0.72
    twimg
    -0.63
     ویکی‌پدی
    -0.61
    tagHelperRunner
    -0.57
    TemporalType
    -0.57
     الحره
    -0.56
     transfieras
    -0.56
    findpost
    -0.52
    SPATH
    -0.50
    ContentAsync
    -0.49
    POSITIVE LOGITS
    ️⃣
    0.54
     stages
    0.48
    fold
    0.46
     months
    0.46
    ⃣
    0.45
     consecutive
    0.45
     Senses
    0.44
    th
    0.43
    months
    0.43
     successive
    0.42
    Activations Density 0.894%

    No Known Activations