© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 7021
    Prev
    Next
    INDEX
    Explanations

    function definitions and their return types in code

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

    Arrow symbols (=>, ->, etc.)

    np_acts-logits-general · gemini-2.0-flash

    arrow function or code syntax

    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
    basicConfig
    -0.60
    IBarButtonItem
    -0.50
    ssymb
    -0.49
    存于互联网档案馆
    -0.47
     âgé
    -0.47
     américain
    -0.47
    señor
    -0.47
     AttributeSet
    -0.47
     indé
    -0.47
    deleteItem
    -0.46
    POSITIVE LOGITS
     =>
    1.38
    =>
    1.10
    )=>
    0.88
    =>$
    0.74
    '=>
    0.72
    "=>
    0.70
    (()=>
    0.70
    Rightarrow
    0.69
    ]=>
    0.68
     <=>
    0.66
    Activations Density 0.169%

    No Known Activations