© 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. 1347
    Prev
    Next
    INDEX
    Explanations

    sections of text that lack any notable activations, indicating it is likely looking for specific structured data or entities that are not present

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

    Follows stop words or punctuation

    np_acts-logits-general · gemini-2.0-flash

    is/be followed by noun

    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
    OGND
    -0.78
     autorytatywna
    -0.78
     betweenstory
    -0.73
     lenker
    -0.71
     تضيفلها
    -0.60
     חיצוניים
    -0.60
    chord
    -0.60
     themſelves
    -0.59
     yyl
    -0.58
     auroit
    -0.58
    POSITIVE LOGITS
     the
    0.66
    requireNonNull
    0.54
     truly
    0.54
     where
    0.53
     an
    0.52
    DebuggerNonUser
    0.51
    ModelSerializer
    0.51
     lī
    0.49
     a
    0.49
    setContentView
    0.48
    Activations Density 0.142%

    No Known Activations