© 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-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 10919
    Prev
    Next
    INDEX
    Explanations

    terms related to architectural features, particularly arches and arcs

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

    relating to arches or arcs

    np_acts-logits-general · gemini-2.0-flash

    arc or arch shape

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ویکی‌پدیا
    -0.52
    ChildScrollView
    -0.51
    PMailer
    -0.50
    SharedDtor
    -0.47
     Creature
    -0.47
    Cartney
    -0.45
    ="@+
    -0.45
    
    -0.45
    /*
    -0.44
    戚
    -0.42
    POSITIVE LOGITS
     arco
    1.54
     arc
    1.51
     arch
    1.51
     Arch
    1.49
     arcos
    1.47
     Arc
    1.44
    arc
    1.43
    Arch
    1.41
    Arc
    1.39
     arches
    1.37
    Activations Density 0.227%

    No Known Activations