© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 27-GEMMASCOPE-RES-16K
    11. 9548
    Prev
    Next
    INDEX
    Explanations

    various numeric patterns and symbols, indicating it is likely focused on data formatting or structure

    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
     Warum
    -0.49
     varones
    -0.48
     why
    -0.47
    ScopeManager
    -0.46
    Warum
    -0.45
    Хьажоргаш
    -0.43
    Categoría
    -0.42
    hombres
    -0.42
    why
    -0.41
     Pourquoi
    -0.41
    POSITIVE LOGITS
     endforeach
    0.43
     Савезне
    0.42
     uParam
    0.42
    itinéraire
    0.42
     GenerationType
    0.41
     unterkunft
    0.40
     localObject
    0.39
     >=",
    0.37
     uLocal
    0.36
     bParam
    0.35
    Activations Density 0.551%

    No Known Activations