© 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. 41-GEMMASCOPE-RES-16K
    11. 10822
    Prev
    Next
    INDEX
    Explanations

    phrases related to discarding and removal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/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.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aislada
    -0.41
    vician
    -0.40
    ślę
    -0.39
     igenom
    -0.38
     yym
    -0.37
    OGND
    -0.37
    MarshalTo
    -0.35
     känna
    -0.35
    rungsseite
    -0.35
     onBind
    -0.34
    POSITIVE LOGITS
     completely
    2.41
     entirely
    2.36
     altogether
    2.23
     Completely
    1.98
    completely
    1.95
    Completely
    1.93
     totally
    1.89
     completamente
    1.75
     complètement
    1.71
     kokona
    1.57
    Activations Density 0.962%

    No Known Activations