© 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. 31-GEMMASCOPE-RES-131K
    11. 13593
    Prev
    Next
    INDEX
    Explanations

    concepts related to assumptions, their impacts on actions, and the influence of attitudes in social contexts

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

    increase or augmentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     nerfs
    -0.67
     downgrade
    -0.66
     lowers
    -0.66
     Minus
    -0.65
     Smaller
    -0.65
     disadvantages
    -0.65
     bajas
    -0.65
     lowering
    -0.64
    Минусы
    -0.63
     downgraded
    -0.63
    POSITIVE LOGITS
     increase
    0.96
     increased
    0.93
     positive
    0.93
     increases
    0.88
    increased
    0.84
    increase
    0.84
     boost
    0.82
    Increased
    0.82
     Increase
    0.81
    Increase
    0.81
    Activations Density 0.851%

    No Known Activations