© 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
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 15998
    Prev
    Next
    INDEX
    Explanations

    phrases related to connection and understanding between concepts or ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnusedPrivate
    -0.43
     Idle
    -0.35
     gese
    -0.33
     reflected
    -0.33
     IDLE
    -0.33
    роза
    -0.32
    ={({
    -0.32
     Refle
    -0.32
    lections
    -0.32
     refle
    -0.32
    POSITIVE LOGITS
     المعيارى
    0.67
    PerformLayout
    0.64
     चीज़ों
    0.63
    IContainer
    0.60
     clues
    0.57
     mystère
    0.57
     TestBed
    0.56
     loopholes
    0.56
     rompecabezas
    0.55
    antaranya
    0.55
    Activations Density 0.547%

    No Known Activations