© 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. 4310
    Prev
    Next
    INDEX
    Explanations

    concepts related to success and achieving goals

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

    followed by punctuation or a dash

    np_acts-logits-general · gemini-2.0-flash

    introducing specifics after general terms

    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
    CodedInputStream
    -0.68
    \{\\
    -0.66
    mybatisplus
    -0.65
    WaitGroup
    -0.60
    ValueStyle
    -0.60
     Lightboxes
    -0.57
    TagMode
    -0.57
     referenties
    -0.56
    ']):
    -0.55
    /');
    -0.55
    POSITIVE LOGITS
     namely
    1.60
     iaitu
    1.45
     Namely
    1.37
     yaitu
    1.36
    namely
    1.34
    那就是
    1.27
     nemlig
    1.26
    —
    1.19
     yakni
    1.19
     یعنی
    1.17
    Activations Density 0.627%

    No Known Activations