© 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 EvalsExportsinterp-engineNEWAPI 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. 8164
    Prev
    Next
    INDEX
    Explanations

    negative sentiments or expressions of doubt and refusal

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

    Follows "not," "never," or "t"

    np_acts-logits-general · gemini-2.0-flash

    negation

    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
     الرياضيه
    -0.52
    脚注の使い方
    -0.49
    jsxFileName
    -0.49
    jmniej
    -0.47
    يكب
    -0.46
    tanleria
    -0.45
    oa̍t
    -0.44
    MethodManager
    -0.44
     péché
    -0.44
    featureID
    -0.43
    POSITIVE LOGITS
     ever
    0.85
     EVER
    0.84
     jamais
    0.69
     Ever
    0.67
    ever
    0.61
    Ever
    0.60
    EVER
    0.59
     jemals
    0.55
     asla
    0.51
     budge
    0.50
    Activations Density 0.206%

    No Known Activations