© 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-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 7145
    Prev
    Next
    INDEX
    Explanations

    preferences and inclinations expressed through the word 'like' and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Paglinawan
    -0.68
    脚注の使い方
    -0.56
    ScreenState
    -0.56
     intptr
    -0.56
    localctx
    -0.54
    asanjo
    -0.54
    ridgeshire
    -0.54
     Commands
    -0.54
    MethodManager
    -0.53
    
    -0.53
    POSITIVE LOGITS
     likes
    2.55
     like
    2.34
    like
    2.34
     Like
    2.27
     LIKE
    2.25
    Like
    2.23
    likes
    2.23
    LIKE
    2.11
     liked
    2.11
     liking
    2.05
    Activations Density 0.215%

    No Known Activations