© 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. 0-GEMMASCOPE-RES-16K
    11. 8960
    Prev
    Next
    INDEX
    Explanations

    instances of the word "carbon."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pri
    -0.61
     plu
    -0.56
     CE
    -0.53
     fle
    -0.52
     sof
    -0.51
     CPS
    -0.50
     liberal
    -0.50
     PSE
    -0.49
     vag
    -0.49
     CAD
    -0.49
    POSITIVE LOGITS
     desmotivaciones
    0.82
     zimowa
    0.81
    ConstraintMaker
    0.77
     miniaturka
    0.77
     amitié
    0.75
     Komunikasi
    0.74
     noDo
    0.73
     ainfi
    0.73
     vectorielle
    0.71
     geométrico
    0.71
    Activations Density 0.258%

    No Known Activations