© 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. 18-GEMMASCOPE-RES-16K
    11. 14207
    Prev
    Next
    INDEX
    Explanations

    assertions or statements related to falsehoods or misinformation

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

    Followed by numbers or units of measure

    np_acts-logits-general · gemini-2.0-flash

    one of a kind

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onomía
    -0.57
    自身
    -0.47
    些
    -0.46
    EXPR
    -0.45
     lần
    -0.45
    届
    -0.44
     second
    -0.44
     little
    -0.44
     slightest
    -0.44
     SEDS
    -0.43
    POSITIVE LOGITS
     saja
    0.82
    AndEndTag
    0.78
     apiece
    0.78
     IBOutlet
    0.73
    Kaynakça
    0.70
     تانيه
    0.68
     sahaja
    0.64
     виправивши
    0.64
    voorbeeld
    0.63
    ñores
    0.62
    Activations Density 0.187%

    No Known Activations