© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 8959
    Prev
    Next
    INDEX
    Explanations

    instances of the word "likes" indicating preferences or affinities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Parabéns
    -0.44
    SearchTree
    -0.44
    {{/
    -0.41
     frango
    -0.40
    Judges
    -0.40
    UFC
    -0.39
    SpringRunner
    -0.39
    战斗
    -0.38
    LANTA
    -0.38
    gemäß
    -0.37
    POSITIVE LOGITS
     likes
    1.93
     loves
    1.47
    likes
    1.46
     Likes
    1.41
     liked
    1.33
    Likes
    1.27
     Loves
    1.13
     liking
    1.12
     favorite
    1.09
     люби
    1.09
    Activations Density 0.057%

    No Known Activations