© 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. 16-GEMMASCOPE-RES-16K
    11. 7934
    Prev
    Next
    INDEX
    Explanations

    instances of entering or being admitted into a space or entity

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

    "enter" and its forms

    np_acts-logits-general · gemini-2.0-flash

    enter into or in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ấy
    -0.62
     harapan
    -0.53
     extradition
    -0.50
     afric
    -0.49
    Wanted
    -0.49
     CHOICE
    -0.48
     Potosí
    -0.47
     initComponents
    -0.47
     distanza
    -0.47
     chré
    -0.47
    POSITIVE LOGITS
     into
    1.24
    Into
    1.10
     Into
    1.06
     INTO
    1.05
    into
    0.98
    enters
    0.90
     enters
    0.89
     entered
    0.83
    INTO
    0.83
    entered
    0.81
    Activations Density 0.130%

    No Known Activations