© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 36-GEMMASCOPE-RES-16K
    11. 8687
    Prev
    Next
    INDEX
    Explanations

    references to data storage and retrieval operations

    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
     (*(
    -0.36
     المر
    -0.34
    "](
    -0.33
    ()(
    -0.33
     ((!
    -0.32
    MathML
    -0.32
    ].(
    -0.31
     Nye
    -0.30
     Heller
    -0.29
    (*(
    -0.29
    POSITIVE LOGITS
    Personendaten
    0.71
    -£
    0.63
    Aholisi
    0.60
     propOrder
    0.59
    EndContext
    0.57
    RTEX
    0.55
     OMITBAD
    0.53
     surla
    0.53
    forChild
    0.51
     CallOverrides
    0.51
    Activations Density 1.718%

    No Known Activations