© 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. 30-GEMMASCOPE-RES-16K
    11. 10657
    Prev
    Next
    INDEX
    Explanations

    expressions of personal opinion or knowledge claims

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

    "As far as I/we know" phrases

    np_acts-logits-general · gemini-2.0-flash

    as far as X know expressions

    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
     pleaſure
    -0.64
     AttributeSet
    -0.54
     Efq
    -0.52
     TableColumn
    -0.52
     itſelf
    -0.51
     ſeveral
    -0.49
     juſt
    -0.49
     bileklik
    -0.48
    anneer
    -0.48
     taşlı
    -0.48
    POSITIVE LOGITS
    知る
    0.54
     aware
    0.50
     knowledge
    0.50
     understanding
    0.50
     known
    0.49
     AFA
    0.49
     sepen
    0.49
     conocimiento
    0.47
     afa
    0.47
     conhecimento
    0.46
    Activations Density 0.351%

    No Known Activations