Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 9080
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to machinery and their operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     spite
    -0.58
    ✨:
    -0.56
     Meksiku
    -0.54
     privatisation
    -0.51
    saraba
    -0.50
     settling
    -0.48
    LookAnd
    -0.48
     kasarigan
    -0.47
     Focusing
    -0.46
     migration
    -0.46
    POSITIVE LOGITS
    hésite
    0.64
     endwhile
    0.64
    setVerticalGroup
    0.62
    Obrázky
    0.61
    DatabaseError
    0.61
    ttino
    0.59
     كومونز
    0.57
    StringCopy
    0.56
    avigation
    0.56
     correctes
    0.56
    Activations Density 0.871%

    No Known Activations