© 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. 28-GEMMASCOPE-RES-16K
    11. 10236
    Prev
    Next
    INDEX
    Explanations

    phrases indicating non-standard or atypical characteristics in various contexts

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

    "Non" prefix

    np_acts-logits-general · gemini-2.0-flash

    non- followed by a word

    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
    ValueStyle
    -0.57
     izdel
    -0.44
    styleType
    -0.44
     capucha
    -0.42
     efficaces
    -0.41
    べき
    -0.40
     guadag
    -0.40
    ungszeit
    -0.40
     desigual
    -0.39
    occupe
    -0.38
    POSITIVE LOGITS
     Non
    1.02
     non
    0.95
    Non
    0.89
     NON
    0.86
    non
    0.82
    NON
    0.79
     Nons
    0.74
     Nong
    0.71
     nons
    0.68
    ノン
    0.64
    Activations Density 0.244%

    No Known Activations