© 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. 20-GEMMASCOPE-RES-16K
    11. 6260
    Prev
    Next
    INDEX
    Explanations

    references to multimedia technology and devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    technical specifications and details about electronic devices, particularly screens and displays.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.38
     서
    -0.38
     stav
    -0.35
     Silber
    -0.33
     West
    -0.32
     Nis
    -0.32
    XCTAssertEqual
    -0.32
     PARAMETER
    -0.32
    sch
    -0.31
    Bibliography
    -0.31
    POSITIVE LOGITS
     screens
    0.76
     screen
    0.75
     Screens
    0.67
     écran
    0.66
    screen
    0.65
     esternos
    0.65
     TVs
    0.63
     display
    0.63
     pantalla
    0.62
     HDTV
    0.61
    Activations Density 0.196%

    No Known Activations