© 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
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 15868
    Prev
    Next
    INDEX
    Explanations

    technical terms related to electronics and computer science

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

    physical objects or entities, particularly those related to infrastructure, technology, or natural resources.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    domain-specific technical or specialized terminology and key subject matter nouns across diverse fields.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    numerusform
    -0.50
     prêtres
    -0.38
     Juifs
    -0.37
     bellezza
    -0.34
     helft
    -0.34
    oporosis
    -0.34
    ociação
    -0.34
    Das
    -0.34
    clerosis
    -0.34
     >=",
    -0.33
    POSITIVE LOGITS
    rungsseite
    0.69
     للمعارف
    0.63
     صوتيه
    0.61
    IUrlHelper
    0.61
     ProtoMessage
    0.57
     components
    0.57
     processes
    0.55
    related
    0.54
     activities
    0.54
     systems
    0.54
    Activations Density 1.084%

    No Known Activations