© 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. 15-GEMMASCOPE-RES-16K
    11. 5139
    Prev
    Next
    INDEX
    Explanations

    HTML attributes and their values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Milne
    -0.47
    SourceChecksum
    -0.46
     Hj
    -0.45
    wakili
    -0.43
    ますね
    -0.43
    XH
    -0.43
    shutil
    -0.42
     CHtml
    -0.42
    onStop
    -0.42
     hjel
    -0.41
    POSITIVE LOGITS
    ="
    1.19
    ='
    0.84
    =\"
    0.71
    ]="
    0.68
    =“
    0.68
    )="
    0.68
    =”
    0.66
    ="../
    0.66
    ="_
    0.65
     autorytatywna
    0.65
    Activations Density 0.191%

    No Known Activations