© 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. 11-GEMMASCOPE-RES-16K
    11. 6438
    Prev
    Next
    INDEX
    Explanations

    phrases that describe the composition or components of a subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/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.11.hook_resid_post
    Hook Layer
    11
    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
    -0.44
     threatened
    -0.40
     späteren
    -0.39
    AppState
    -0.39
    threat
    -0.38
     jopa
    -0.38
     שוליים
    -0.38
     lejos
    -0.38
    <bos>
    -0.38
    perhaps
    -0.37
    POSITIVE LOGITS
     consists
    1.47
     consisted
    1.45
     consisting
    1.41
     comprised
    1.36
     consist
    1.30
     comprises
    1.25
     comprising
    1.21
     composed
    1.20
     består
    1.18
     comprise
    1.16
    Activations Density 0.370%

    No Known Activations