© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 8565
    Prev
    Next
    INDEX
    Explanations

    specific names, terms, or identifiers associated with various subjects or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.68
    pertory
    -0.52
    XmlIgnore
    -0.50
     OMITBAD
    -0.49
    UpdatedBy
    -0.48
     endblock
    -0.47
    Рис
    -0.47
     objekt
    -0.47
     réservoir
    -0.46
     inhabitant
    -0.46
    POSITIVE LOGITS
    Iain
    0.63
     Iain
    0.63
    iai
    0.58
    iau
    0.57
    IEW
    0.56
    ais
    0.56
    lain
    0.56
    AIN
    0.54
    ail
    0.54
    ain
    0.54
    Activations Density 5.186%

    No Known Activations