© 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. 36-GEMMASCOPE-RES-16K
    6. 7719
    Prev
    Next
    INDEX
    Explanations

    language related to missing or lost opportunities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ulang
    -0.41
    annica
    -0.40
     رسمی
    -0.35
    sizeCache
    -0.35
    ArgsConstructor
    -0.34
    tronic
    -0.34
     citoyens
    -0.33
    hnung
    -0.33
     المختلفة
    -0.33
    yeur
    -0.33
    POSITIVE LOGITS
    Missed
    0.81
     Missed
    0.75
     missed
    0.75
     deadlines
    0.67
    missed
    0.66
     misses
    0.65
     miss
    0.64
     Missing
    0.61
     crucial
    0.57
    miss
    0.56
    Activations Density 0.169%

    No Known Activations