© 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. 20-GEMMASCOPE-RES-16K
    11. 7864
    Prev
    Next
    INDEX
    Explanations

    elements relating to personal identity and transformation in a narrative context

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

    before personal pronouns

    np_acts-logits-general · gemini-2.0-flash

    who you are and becoming

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebElementEntity
    -0.57
    queryInterface
    -0.54
    例句
    -0.51
    Rüyada
    -0.48
     endblock
    -0.47
    ChildIndex
    -0.46
    oredCriteria
    -0.46
    ApiModel
    -0.45
    setupUi
    -0.45
    >({
    -0.45
    POSITIVE LOGITS
     who
    1.60
     Who
    1.29
    who
    1.28
    Who
    1.28
     hvem
    1.25
     quién
    1.15
     siapa
    1.06
     ourselves
    1.05
    WHO
    1.02
     WHO
    1.01
    Activations Density 0.212%

    No Known Activations