© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 27-GEMMASCOPE-RES-16K
    11. 11286
    Prev
    Next
    INDEX
    Explanations

    conditional statements and references to examples or scenarios in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.50
     čierna
    -0.45
     tilbage
    -0.42
     dámské
    -0.42
    Personensuche
    -0.42
     király
    -0.41
     possibilidades
    -0.41
     gezicht
    -0.40
     fotográfico
    -0.40
     meisje
    -0.40
    POSITIVE LOGITS
    withstanding
    0.78
    verwijspagina
    0.69
    ?)
    0.67
    Personendaten
    0.66
    ?),
    0.63
    !)
    0.62
    )."
    0.61
    ?).
    0.60
    ),"
    0.59
    skjaer
    0.57
    Activations Density 1.020%

    No Known Activations