© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 15414
    Prev
    Next
    INDEX
    Explanations

    phrases indicating negation or denial

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

    Following "Not" expressing some kind of sentiment

    np_acts-logits-general · gemini-2.0-flash

    not followed by qualifiers

    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
     Autorizaciones
    -0.38
     rostro
    -0.36
     compan
    -0.35
     gly
    -0.33
     libéral
    -0.33
    Хьажоргаш
    -0.33
    printList
    -0.32
     sequelize
    -0.31
     SwitchCompat
    -0.31
    inSlope
    -0.31
    POSITIVE LOGITS
     impressed
    0.66
     glad
    0.60
     pleased
    0.59
     tempted
    0.59
     Wikiseite
    0.59
     afraid
    0.59
     thankful
    0.58
     impossible
    0.56
     interested
    0.55
    istoitu
    0.55
    Activations Density 0.255%

    No Known Activations