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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 30-GEMMASCOPE-RES-16K
    6. 10299
    Prev
    Next
    INDEX
    Explanations

    references to social or political issues affecting communities

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

    followed by adverbs like "somewhat" or "definitely"

    np_acts-logits-general · gemini-2.0-flash

    somewhat qualified outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     super
    -0.35
     perfe
    -0.29
     Perfect
    -0.28
     perfect
    -0.25
     perfecto
    -0.25
     '../../../../
    -0.25
     preference
    -0.24
     envie
    -0.24
     súper
    -0.24
     Besonders
    -0.24
    POSITIVE LOGITS
     immerhin
    1.38
    somewhat
    1.34
     somewhat
    1.30
     marginally
    1.30
     decently
    1.23
     einiger
    1.23
     moderately
    1.23
     tolerably
    1.22
     Somewhat
    1.21
    Somewhat
    1.21
    Activations Density 0.979%

    No Known Activations