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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 11404
    Prev
    Next
    INDEX
    Explanations

    technical terms and operations related to input/output (I/O) processes

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

    systems programming code related to I/O operations and file handling.

    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
     ujednoznacz
    -0.56
    Życiorys
    -0.54
     utafitiHapana
    -0.54
     يتيمه
    -0.53
    rungsseite
    -0.52
    InjectAttribute
    -0.51
     ویکی‌پدیا
    -0.49
    Havolalar
    -0.47
    niſſe
    -0.47
     EconPapers
    -0.47
    POSITIVE LOGITS
    bufio
    0.51
    readline
    0.44
    libft
    0.40
    fromCharCode
    0.36
     readline
    0.36
     flush
    0.36
    send
    0.36
    Попис
    0.35
     recv
    0.35
     send
    0.34
    Activations Density 0.516%

    No Known Activations