© 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. 11260
    Prev
    Next
    INDEX
    Explanations

    connections between historical events and their implications for society

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

    words that affirm or validate a statement as true or correct.

    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
     Obviously
    -0.66
    Personendaten
    -0.66
     obviously
    -0.64
    obviously
    -0.63
    Obviously
    -0.60
     obvious
    -0.56
     évidemment
    -0.56
     Clearly
    -0.56
    でしょう
    -0.55
    だろう
    -0.54
    POSITIVE LOGITS
     actually
    2.41
    actually
    2.11
    Actually
    1.95
     Actually
    1.94
     ACTUALLY
    1.66
     faktisk
    1.64
     faktiskt
    1.62
    実は
    1.60
     aslında
    1.48
    其實
    1.41
    Activations Density 0.815%

    No Known Activations