© 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. 18-GEMMASCOPE-RES-16K
    11. 9600
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a need for support or resources in relation to facilities and care

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

    Preceding words followed by "so"

    np_acts-logits-general · gemini-2.0-flash

    so or such

    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
    wnież
    -0.54
     accordingly
    -0.53
    =$?
    -0.52
     jedenfalls
    -0.49
    ients
    -0.47
     derfor
    -0.47
    cutt
    -0.46
    érience
    -0.46
    бва
    -0.46
    Alguna
    -0.45
    POSITIVE LOGITS
     such
    2.11
     so
    1.90
     tão
    1.90
    such
    1.82
     tantas
    1.82
    這麼
    1.75
     इत
    1.73
     tantos
    1.71
     столь
    1.71
    如此
    1.71
    Activations Density 0.597%

    No Known Activations