© 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. 33-GEMMASCOPE-RES-16K
    11. 10447
    Prev
    Next
    INDEX
    Explanations

    specific identifiers or codes related to scientific classifications or categorizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    in
    -0.59
    ا
    -0.58
    y
    -0.56
    is
    -0.55
    j
    -0.45
    ed
    -0.44
    ből
    -0.44
    as
    -0.44
    at
    -0.43
    ו
    -0.42
    POSITIVE LOGITS
    parsedMessage
    1.09
    featureID
    0.85
    хьтан
    0.80
    <bos>
    0.78
    SharedCtor
    0.76
    <unused43>
    0.74
    <pad>
    0.73
     houſe
    0.73
    <unused41>
    0.72
    oredCriteria
    0.72
    Activations Density 1.633%

    No Known Activations