© 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. 24-GEMMASCOPE-RES-16K
    11. 5015
    Prev
    Next
    INDEX
    Explanations

    negative connotations or experiences related to denials and absences

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

    followed by punctuation or prepositions

    np_acts-logits-general · gemini-2.0-flash

    things denied or ineffective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XmlAccessorType
    -0.42
    ขึ้น
    -0.40
    角
    -0.35
     youngsters
    -0.34
     chapa
    -0.34
    fxml
    -0.34
    setModal
    -0.33
    ぐれ
    -0.33
    JLabel
    -0.32
    restrictions
    -0.32
    POSITIVE LOGITS
     defaultstate
    0.73
    httphttps
    0.59
    featureID
    0.56
     <<<<<<<<<<<<<<
    0.55
    aarrggbb
    0.55
     kaynağından
    0.54
     HttpNotFound
    0.54
    áctenos
    0.52
     ControllerBase
    0.50
     irrelevant
    0.50
    Activations Density 0.997%

    No Known Activations