© 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. 10-GEMMASCOPE-RES-16K
    11. 7356
    Prev
    Next
    INDEX
    Explanations

    phrases that describe the composition or structure of entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ironically
    -0.47
     שוליים
    -0.46
     condicion
    -0.41
    脚注の使い方
    -0.40
     späteren
    -0.40
    AppState
    -0.40
     perlindungan
    -0.39
    certainly
    -0.39
     obliquely
    -0.39
    attenzione
    -0.39
    POSITIVE LOGITS
     consisting
    1.49
     consists
    1.48
     consisted
    1.48
     comprised
    1.36
     consist
    1.36
     composed
    1.28
     comprising
    1.22
     består
    1.21
     comprises
    1.20
     terdiri
    1.15
    Activations Density 0.476%

    No Known Activations