© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 10356
    Prev
    Next
    INDEX
    Explanations

    words related to writing and personal expression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Билгалдахарш
    -0.37
    corrência
    -0.36
    personnel
    -0.35
     personnel
    -0.35
    msgTypes
    -0.34
     overall
    -0.33
     efficient
    -0.33
    яр
    -0.32
     respeito
    -0.32
    setContentView
    -0.31
    POSITIVE LOGITS
     random
    0.54
     randomly
    0.53
    random
    0.51
     verſch
    0.50
    Random
    0.49
     nahilalakip
    0.48
     intercamb
    0.47
     Random
    0.47
    cognito
    0.47
     RANDOM
    0.47
    Activations Density 0.237%

    No Known Activations