© 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. 9852
    Prev
    Next
    INDEX
    Explanations

    terms related to the manner or way in which actions are performed

    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
     šk
    -0.37
     berguna
    -0.36
     yardım
    -0.36
     nahilalakip
    -0.34
     voordeel
    -0.34
     proszę
    -0.33
     réun
    -0.33
     ugy
    -0.33
     coû
    -0.32
    ésult
    -0.32
    POSITIVE LOGITS
    manner
    0.85
     manner
    0.85
    twimg
    0.74
     Manner
    0.74
     manier
    0.72
    posób
    0.71
     autorytatywna
    0.71
     differently
    0.71
     way
    0.71
     manière
    0.69
    Activations Density 0.287%

    No Known Activations