© 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. 24-GEMMASCOPE-RES-16K
    11. 8432
    Prev
    Next
    INDEX
    Explanations

    the presence of repeated or similar patterns of characters

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

    "p" followed by two letters

    np_acts-logits-general · gemini-2.0-flash

    words starting with p

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    $_['
    -0.57
     HttpNotFound
    -0.56
    Vidite
    -0.55
    thâu
    -0.52
     OMITBAD
    -0.52
    ніципа
    -0.51
     Liberties
    -0.50
    ly
    -0.49
    t
    -0.48
     ơn
    -0.48
    POSITIVE LOGITS
    RectangleBorder
    0.63
    Datuak
    0.56
     kasarigan
    0.54
    ConstraintMaker
    0.51
    Espèce
    0.50
    centralwidget
    0.50
     matéri
    0.49
    StructEnd
    0.47
    Chel
    0.46
     AssemblyTitle
    0.46
    Activations Density 0.211%

    No Known Activations