© 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. 201
    Prev
    Next
    INDEX
    Explanations

    technical terms and specific variables related to computer and network security

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

    articles and demonstrative pronouns (especially "the" and "a") that appear in technical or formal writing contexts.

    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
    OGND
    -0.60
    AutoField
    -0.54
     HasFactory
    -0.53
     defStyleAttr
    -0.53
    NameInMap
    -0.52
     surla
    -0.52
    sizeCache
    -0.51
    errHandler
    -0.50
    __.__
    -0.49
    bitField
    -0.48
    POSITIVE LOGITS
     corresponding
    2.58
     associated
    2.41
    corresponding
    2.23
     related
    2.22
     correspondiente
    1.95
     Corresponding
    1.94
    associated
    1.93
     accompanying
    1.92
     соответству
    1.77
    Corresponding
    1.77
    Activations Density 1.365%

    No Known Activations