© 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. 5614
    Prev
    Next
    INDEX
    Explanations

    negative phrases and concepts related to expectations and limitations

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

    following prepositions

    np_acts-logits-general · gemini-2.0-flash

    describing states or qualities

    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
    parsedMessage
    -0.53
    ༘
    -0.46
    цезда
    -0.42
     Wicidata
    -0.39
     Numerade
    -0.38
    馃
    -0.37
    aimer
    -0.37
     objet
    -0.35
    featureID
    -0.35
    المشاركات
    -0.34
    POSITIVE LOGITS
     AssemblyTitle
    0.61
    TagMode
    0.57
    shortcuts
    0.54
     stereotypical
    0.48
     superficial
    0.46
     stereotyp
    0.45
     silos
    0.45
     unrealistic
    0.45
     hierarchical
    0.45
     rigidity
    0.45
    Activations Density 0.348%

    No Known Activations