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-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 6323
    Prev
    Next
    INDEX
    Explanations

    JavaScript DOM manipulation commands and methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     facie
    -0.65
    haway
    -0.63
    xase
    -0.62
     IMPLIED
    -0.60
    RunWith
    -0.60
    erdings
    -0.59
     AssemblyCulture
    -0.57
    testify
    -0.57
    setVerticalGroup
    -0.57
    peek
    -0.57
    POSITIVE LOGITS
    getElementById
    1.43
    querySelector
    1.22
    querySelectorAll
    0.94
    createElement
    0.86
    getElementsBy
    0.85
     XMLHttpRequest
    0.67
     AttributeSet
    0.67
    UserScript
    0.66
     ElementRef
    0.66
    documentElement
    0.64
    Activations Density 0.076%

    No Known Activations