© 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. 28-GEMMASCOPE-RES-16K
    11. 5195
    Prev
    Next
    INDEX
    Explanations

    instances of the word "follow" and its variations, indicating a focus on following actions or advice

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

    The token "follow" or its translations/forms

    np_acts-logits-general · gemini-2.0-flash

    following words like 'his', 'through', 'the', 'this'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    apimachinery
    -0.43
    #![
    -0.42
     MTS
    -0.42
    bitField
    -0.41
     Garg
    -0.39
    
    -0.38
     met
    -0.38
    #
    -0.37
    intervento
    -0.37
    pdu
    -0.37
    POSITIVE LOGITS
    follow
    0.75
     Follow
    0.72
     follow
    0.72
     Suivez
    0.70
     FOLLOW
    0.70
    Follow
    0.70
     suivre
    0.68
     suiv
    0.64
     mengikuti
    0.63
     suivez
    0.63
    Activations Density 0.153%

    No Known Activations