Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 9107
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to semiconductor manufacturing processes

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

    technical terms related to semiconductor manufacturing and vacuum chambers, particularly around etching, sputtering, and pressure measurements.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '\\;'
    -0.69
     EconPapers
    -0.52
     ویکی‌پدی
    -0.48
     noten
    -0.45
     дописавши
    -0.44
    !*\
    -0.40
    PreferredItem
    -0.37
     CanadaChoose
    -0.37
    ECT
    -0.37
    Tembelea
    -0.36
    POSITIVE LOGITS
    IsMutable
    0.42
    -};
    0.41
    پیش
    0.39
    ConverterFactory
    0.39
    buquerque
    0.39
     considérons
    0.38
     Vacuum
    0.38
    PerformLayout
    0.38
    lwjgl
    0.38
    Kaieteur
    0.38
    Activations Density 0.735%

    No Known Activations