© 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. 8-GEMMASCOPE-RES-16K
    11. 11050
    Prev
    Next
    INDEX
    Explanations

    specific Japanese characters or phrases related to emotions and states of being

    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
     in
    -0.75
     mxArray
    -0.70
    ValueStyle
    -0.61
    국의
    -0.57
    étape
    -0.57
    in
    -0.56
     a
    -0.55
    a
    -0.54
     from
    -0.54
    thenia
    -0.53
    POSITIVE LOGITS
     Reſ
    1.09
     Inſ
    1.02
     Conſ
    1.01
     Anſ
    1.00
     Diſ
    0.96
     Efq
    0.95
     Houſe
    0.91
     myſelf
    0.90
     Perſ
    0.87
     ſtate
    0.87
    Activations Density 0.274%

    No Known Activations