© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 8467
    Prev
    Next
    INDEX
    Explanations

    phrases that express the act of doing something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ویکی‌پدی
    -0.55
    RectangleBorder
    -0.45
     ModelExpression
    -0.43
    IsContent
    -0.40
     îna
    -0.40
     varargin
    -0.40
     Vordergrund
    -0.38
    tská
    -0.38
    せっかく
    -0.37
     împre
    -0.37
    POSITIVE LOGITS
     occurs
    0.53
    énieurs
    0.52
     happens
    0.49
     occur
    0.48
    üyor
    0.48
    profil
    0.48
     happen
    0.47
     Chriftian
    0.47
    <bos>
    0.45
     happened
    0.45
    Activations Density 0.190%

    No Known Activations