© 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. 301
    Prev
    Next
    INDEX
    Explanations

    terms related to biological and medical processes, especially concerning apoptosis and its modulation

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

    followed by "are"

    np_acts-logits-general · gemini-2.0-flash

    describing what nouns are

    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
     was
    -0.92
     is
    -0.90
     has
    -0.77
    was
    -0.72
     hasn
    -0.70
     does
    -0.70
    has
    -0.70
    Has
    -0.68
     isn
    -0.68
     Has
    -0.68
    POSITIVE LOGITS
     are
    2.53
     were
    2.06
     aren
    1.64
    are
    1.64
     ARE
    1.60
    were
    1.54
     weren
    1.48
     WERE
    1.47
    Are
    1.43
     have
    1.40
    Activations Density 4.584%

    No Known Activations