© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 36083
    Prev
    Next
    INDEX
    Explanations

    geographical locations and associated metadata in news articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    city and state names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ðsíða
    -0.91
    ésultats
    -0.84
     Waſſer
    -0.84
     ſei
    -0.83
     Verſ
    -0.82
     increí
    -0.80
     geſch
    -0.79
     témoig
    -0.79
     indígen
    -0.79
     GOtt
    -0.78
    POSITIVE LOGITS
     —
    0.47
     -
    0.44
     HasFactory
    0.36
     –
    0.35
     --
    0.34
    )
    0.33
     If
    0.31
    .
    0.31
     (
    0.30
     An
    0.30
    Activations Density 0.007%

    No Known Activations