© 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. 15-GEMMASCOPE-RES-16K
    11. 4402
    Prev
    Next
    INDEX
    Explanations

    HTML header tags in a structured document

    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
     parís
    -0.55
    thschild
    -0.52
     Palestina
    -0.50
    odziel
    -0.48
     saveiro
    -0.48
    adaş
    -0.47
    jalá
    -0.47
    SerializeField
    -0.47
     sauvage
    -0.47
     nuclé
    -0.46
    POSITIVE LOGITS
    </h2>
    1.21
    </h3>
    1.10
    </h1>
    1.07
    </h6>
    1.05
    </h4>
    1.02
    </h5>
    1.01
     Audiodateien
    0.80
    </table>
    0.77
     }}$}
    0.76
    }*/
    0.71
    Activations Density 0.028%

    No Known Activations