Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 9093
    Prev
    Next
    INDEX
    Explanations

    mathematical representations and symbols explaining physical properties and relationships

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

    Comes before "is" or "represents"

    np_acts-logits-general · gemini-2.0-flash

    definitions and equations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    Datuak
    -0.43
     feroit
    -0.41
     Ανακτήθηκε
    -0.40
     samarbe
    -0.40
    ariConfig
    -0.37
     Appointments
    -0.36
     auroit
    -0.36
     tombe
    -0.35
     pelúcia
    -0.35
    kész
    -0.35
    POSITIVE LOGITS
    adaptiveStyles
    0.65
     EconPapers
    0.58
    OGND
    0.57
     وتسجيلات
    0.56
    RTEX
    0.53
    GEBURTS
    0.53
    addCriterion
    0.52
    AddTagHelper
    0.51
     للمعارف
    0.50
     autorytatywna
    0.49
    Activations Density 0.617%

    No Known Activations