© 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. 5360
    Prev
    Next
    INDEX
    Explanations

    phrases related to social dynamics and interactions

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

    Following "it" or "there"

    np_acts-logits-general · gemini-2.0-flash

    existence, state, or circumstance

    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
     belongs
    -0.54
    belongs
    -0.54
    -0.46
     belong
    -0.46
    pung
    -0.45
     دارد
    -0.43
     Ches
    -0.42
    belong
    -0.42
    umani
    -0.41
    ipot
    -0.41
    POSITIVE LOGITS
    Autoritní
    0.84
    tagHelperRunner
    0.82
     autorytatywna
    0.77
     ModelExpression
    0.73
     <<<<<<<<<<<<<<
    0.69
    Personendaten
    0.68
    EndInit
    0.68
     Signalez
    0.67
    IUrlHelper
    0.65
    +#+#
    0.63
    Activations Density 0.363%

    No Known Activations