© 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. 191
    Prev
    Next
    INDEX
    Explanations

    questions regarding consumer preferences and insights

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

    questions that invite reader perspective or opinion.

    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
    ContentAsync
    -0.67
    XmlAccessorType
    -0.66
    addPreferredGap
    -0.65
    DockStyle
    -0.58
     незавершена
    -0.57
    featureID
    -0.57
    InputBorder
    -0.57
     autorytatywna
    -0.54
     المعيارى
    -0.53
    pushFollow
    -0.53
    POSITIVE LOGITS
     does
    0.77
     did
    0.71
     do
    0.70
     is
    0.69
     are
    0.55
     was
    0.53
     Did
    0.52
     Do
    0.50
     Does
    0.47
    Did
    0.47
    Activations Density 0.310%

    No Known Activations