© 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. 22-GEMMASCOPE-RES-16K
    11. 13337
    Prev
    Next
    INDEX
    Explanations

    elements related to programming structures and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    niſſe
    -1.14
     autorytatywna
    -1.14
    
    -1.10
     lenker
    -1.07
    ſſung
    -1.07
    iſchen
    -1.05
    ロウィン
    -1.05
     témoig
    -1.04
    iſen
    -1.03
     disambiguazione
    -1.02
    POSITIVE LOGITS
    ↵↵
    0.75
    </table>
    0.60
    .
    0.58
    1
    0.49
    ↵↵↵↵
    0.48
    ↵↵↵
    0.48
     
    0.44
     In
    0.41
    }
    0.41
    section
    0.40
    Activations Density 0.273%

    No Known Activations