© 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. 10-GEMMASCOPE-RES-16K
    11. 1867
    Prev
    Next
    INDEX
    Explanations

    data structures and types used in programming, particularly in object-oriented contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     newVal
    -0.68
    存于互联网档案馆
    -0.67
     bookId
    -0.60
     âgé
    -0.58
    AsUp
    -0.58
     Drapeau
    -0.58
     Poincar
    -0.58
    OGND
    -0.57
     itſelf
    -0.56
     becauſe
    -0.53
    POSITIVE LOGITS
    synthesize
    0.84
     ActionResult
    0.79
    seteq
    0.77
    IActionResult
    0.74
    onedDateTime
    0.71
     $("#
    0.70
    therford
    0.70
    ContentValues
    0.70
    <%=
    0.69
     MemoryStream
    0.69
    Activations Density 0.111%

    No Known Activations