© 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. 7291
    Prev
    Next
    INDEX
    Explanations

    terms related to coding and programming functions

    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
     linkovi
    -0.51
     ujednoznacz
    -0.47
    AsUp
    -0.44
     sere
    -0.43
     Ecole
    -0.43
    дино
    -0.42
    CreateMap
    -0.42
    tinyos
    -0.41
     uska
    -0.41
     Grain
    -0.41
    POSITIVE LOGITS
    FailureListener
    0.42
     élastique
    0.42
     sticker
    0.41
    AxisAlignment
    0.40
     romantique
    0.40
     suelos
    0.40
     mencetak
    0.39
     manifested
    0.39
    Amicalement
    0.39
     lui
    0.38
    Activations Density 1.700%

    No Known Activations