© 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. 36-GEMMASCOPE-RES-16K
    6. 7300
    Prev
    Next
    INDEX
    Explanations

    specific legal standards or regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IsMutable
    -0.53
     Bewußt
    -0.52
     שוליים
    -0.45
     transfieras
    -0.45
    recated
    -0.45
     Alltag
    -0.45
     beginnetje
    -0.44
     Betrag
    -0.44
    évaluateur
    -0.44
    citement
    -0.43
    POSITIVE LOGITS
     §
    0.51
     (§
    0.50
     Sach
    0.41
    jsii
    0.40
    bean
    0.39
    AddHtmlAttribute
    0.39
    toThrow
    0.37
     Beau
    0.37
     Agreed
    0.36
     esposo
    0.36
    Activations Density 0.175%

    No Known Activations