© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 11983
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty or questioning correctness

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

    Statements indicating something is incorrect

    np_acts-logits-general · gemini-2.0-flash

    wrong or incorrect

    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
     sula
    -0.62
     насељу
    -0.58
    ostante
    -0.53
     gepubliceerd
    -0.49
    Underline
    -0.49
     Stä
    -0.47
     honnête
    -0.47
     exhaustion
    -0.46
    tainen
    -0.46
    uelles
    -0.45
    POSITIVE LOGITS
     wrong
    1.14
     off
    0.91
     Wrong
    0.91
    wrong
    0.89
     amiss
    0.86
     CreateTagHelper
    0.82
     incorrect
    0.81
    yntaxException
    0.81
    Wrong
    0.81
     WRONG
    0.77
    Activations Density 0.316%

    No Known Activations