© 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. 28-GEMMASCOPE-RES-16K
    11. 7890
    Prev
    Next
    INDEX
    Explanations

    questions or statements of reasoning related to topics of moral or ethical consideration

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

    "because" or similar causal words

    np_acts-logits-general · gemini-2.0-flash

    because

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Comprometido
    -0.64
    contentLoaded
    -0.63
    IntoConstraints
    -0.62
    featureID
    -0.61
    errHandler
    -0.56
     deſſen
    -0.55
     artesanales
    -0.55
    aarrggbb
    -0.55
    :✨
    -0.54
     geweſen
    -0.53
    POSITIVE LOGITS
     because
    0.88
    because
    0.74
     Because
    0.70
    Because
    0.69
    是因为
    0.65
     porque
    0.63
     reasons
    0.61
     simply
    0.59
     때문
    0.57
     BECAUSE
    0.56
    Activations Density 0.324%

    No Known Activations