© 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. 3-GEMMASCOPE-RES-16K
    11. 13119
    Prev
    Next
    INDEX
    Explanations

    instances of the word "followed."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 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
    ooth
    -0.64
    êmios
    -0.64
    alous
    -0.63
    ık
    -0.58
    rī
    -0.58
    tvguidetime
    -0.58
    astrar
    -0.57
    ◄
    -0.57
     Tash
    -0.57
    AnchorStyles
    -0.56
    POSITIVE LOGITS
     followed
    2.47
    followed
    2.19
     Followed
    2.10
    Followed
    1.98
     diikuti
    1.77
     suivie
    1.67
     accompanied
    1.65
     seguido
    1.58
     acompañado
    1.51
     accompagné
    1.48
    Activations Density 0.150%

    No Known Activations