© 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. 20-GEMMASCOPE-RES-16K
    6. 6197
    Prev
    Next
    INDEX
    Explanations

    terms related to printing technology and its applications

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

    detailed technical descriptions about printers and printing technology.

    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
     externi
    -0.46
    กระท
    -0.42
     słucha
    -0.42
     vọng
    -0.41
    GGLE
    -0.40
    expliquer
    -0.39
    raszam
    -0.38
     useCallback
    -0.37
     énergétique
    -0.36
    ismus
    -0.36
    POSITIVE LOGITS
     printers
    0.91
     printing
    0.91
     Printing
    0.89
     printer
    0.86
     inkjet
    0.83
     Printers
    0.82
    Printing
    0.81
     Printer
    0.81
    printer
    0.72
    printing
    0.72
    Activations Density 0.298%

    No Known Activations