© 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-2-2B
    7. Residual Stream - 16k
    9. 6-GEMMASCOPE-RES-16K
    11. 12059
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with biological processes and systems, particularly focusing on apoptosis, neurobiology, and cardiac functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    featureID
    -0.69
    ValueGenerated
    -0.68
     and
    -0.65
     fallu
    -0.60
     وتسجيلات
    -0.59
    AnchorStyles
    -0.59
     mères
    -0.58
    utilisons
    -0.58
     kuitenkin
    -0.58
    İstinadlar
    -0.57
    POSITIVE LOGITS
    prefixer
    0.60
     utafitiHapana
    0.59
     alike
    0.56
     تضيفلها
    0.54
    TintMode
    0.54
    >();
    0.54
    luor
    0.53
    '):
    0.51
     незавершена
    0.51
     will
    0.50
    Activations Density 1.654%

    No Known Activations