© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 7788
    Prev
    Next
    INDEX
    Explanations

    the presence of the token 'mi' in various contexts, likely indicating mentions of individuals or entities

    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
     pressed
    -0.48
     Fore
    -0.46
     fore
    -0.45
    parsedMessage
    -0.41
     pretty
    -0.41
     gains
    -0.40
     cuidad
    -0.40
     schließt
    -0.40
     enhancements
    -0.40
    SourceChecksum
    -0.40
    POSITIVE LOGITS
     mi
    1.33
    mi
    1.30
     Mi
    1.13
    Mi
    1.12
    MI
    1.09
     MI
    0.98
     فريبيس
    0.62
    adaptiveStyles
    0.58
    twimg
    0.51
     Mih
    0.51
    Activations Density 0.081%

    No Known Activations