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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 7198
    Prev
    Next
    INDEX
    Explanations

    phrases indicating errors or issues related to user accounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PreferredItem
    -0.76
     ainfi
    -0.69
     myſelf
    -0.69
     muualla
    -0.69
     ويكيميديا
    -0.65
     استنادى
    -0.65
    ReusableCell
    -0.64
     Monfieur
    -0.62
     fevere
    -0.62
    Personendaten
    -0.62
    POSITIVE LOGITS
    mo
    0.58
    Izvori
    0.55
    tiftung
    0.54
     S
    0.53
    inter
    0.53
     "
    0.52
     Tra
    0.52
     Inter
    0.52
     G
    0.52
     inter
    0.52
    Activations Density 0.496%

    No Known Activations