© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 66678
    Prev
    Next
    INDEX
    Explanations

    keywords related to hierarchical structures and components in a coding context

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

    root element or node

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    FileDialog
    -0.53
    ьаж
    -0.52
    TagMode
    -0.47
    MIDDLEWARE
    -0.46
    MediaStore
    -0.46
     jsPsych
    -0.46
    toThrow
    -0.45
    qtype
    -0.45
     makeStyles
    -0.44
     miniaturka
    -0.44
    POSITIVE LOGITS
    Root
    2.72
     Root
    2.25
    ROOT
    1.63
    getRoot
    1.63
     ROOT
    1.57
    root
    1.52
     Roots
    1.34
    Roots
    1.32
     root
    1.28
     根
    1.13
    Activations Density 0.004%

    No Known Activations