© 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. 22-GEMMASCOPE-RES-16K
    11. 8253
    Prev
    Next
    INDEX
    Explanations

    instances of the word "follow" and its variations that indicate following or tracking information

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

    "Follow" and subsequent actions/directions

    np_acts-logits-general · gemini-2.0-flash

    follow instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tembelea
    -0.61
    astă
    -0.60
     BoxFit
    -0.57
    OptionsMenu
    -0.55
    beginn
    -0.54
     власти
    -0.52
    cadora
    -0.52
     bahawa
    -0.51
     Winaray
    -0.51
     vectorielles
    -0.50
    POSITIVE LOGITS
     suit
    1.42
     closely
    0.98
    suit
    0.97
     suite
    0.88
     Suit
    0.87
     footsteps
    0.86
    Suit
    0.86
     suits
    0.82
    suits
    0.79
    suite
    0.76
    Activations Density 0.126%

    No Known Activations