© 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. 14-GEMMASCOPE-RES-16K
    11. 9815
    Prev
    Next
    INDEX
    Explanations

    instances of the word "appear" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ostante
    -0.61
    ientras
    -0.58
     zelve
    -0.55
     ajutor
    -0.54
     mesma
    -0.54
     kesalahan
    -0.53
     argint
    -0.53
    zelfde
    -0.52
     lieben
    -0.51
    tocin
    -0.50
    POSITIVE LOGITS
     appear
    1.20
     appearance
    1.20
     Appear
    1.16
    Appear
    1.14
     appearing
    1.11
     Appearance
    1.09
    appear
    1.08
     appearances
    1.07
     appears
    1.06
     appeared
    1.05
    Activations Density 0.082%

    No Known Activations