© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 4407
    Prev
    Next
    INDEX
    Explanations

    numerical data and figures related to economic or financial contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows a numerical value

    np_acts-logits-general · gemini-2.0-flash

    sentence end punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __':
    -0.82
    rungsseite
    -0.75
    fromnode
    -0.72
     Infatti
    -0.67
    曖昧さ回避
    -0.66
    __":
    -0.64
     تضيفلها
    -0.63
    tdessen
    -0.62
     infatti
    -0.59
     nemlig
    -0.59
    POSITIVE LOGITS
     Considering
    0.86
    Considering
    0.81
     That
    0.79
     Clearly
    0.78
    Clearly
    0.77
    That
    0.73
    这是什么
    0.72
    Yikes
    0.72
     Damit
    0.70
     compared
    0.69
    Activations Density 0.436%

    No Known Activations