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. 24-GEMMASCOPE-RES-16K
    6. 1096
    Prev
    Next
    INDEX
    Explanations

    technical terms and jargon related to programming, specifically those involving zones and zip files

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

    Starts with the letter "Z"

    np_acts-logits-general · gemini-2.0-flash

    words starting with z

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    include
    -0.52
     Infórmanos
    -0.50
    s
    -0.45
     Harrington
    -0.44
     niech
    -0.43
    i
    -0.42
    contentPadding
    -0.42
     trasero
    -0.41
    ham
    -0.41
    ApiModelProperty
    -0.41
    POSITIVE LOGITS
     Zinc
    0.82
    Zinc
    0.78
     Zat
    0.77
     Zoning
    0.77
     Zin
    0.75
    Zag
    0.73
     Zink
    0.72
    zinc
    0.72
     Zane
    0.71
     zinc
    0.71
    Activations Density 0.363%

    No Known Activations