© 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. 10707
    Prev
    Next
    INDEX
    Explanations

    instances of standing or being positioned in front of someone or something

    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
    tagHelperRunner
    -0.46
     spise
    -0.36
     pourtant
    -0.36
     espirituales
    -0.35
    zają
    -0.35
     todėl
    -0.33
    anlagen
    -0.33
     vinden
    -0.33
    bale
    -0.32
     Kramer
    -0.32
    POSITIVE LOGITS
     standing
    0.80
     debout
    0.68
     invokingState
    0.67
     Standing
    0.66
     stood
    0.64
     المعيارى
    0.63
    Standing
    0.62
    站在
    0.62
    AxisAlignment
    0.59
    MLLoader
    0.58
    Activations Density 0.276%

    No Known Activations