© 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-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 1302
    Prev
    Next
    INDEX
    Explanations

    specific patterns involving single and double quotes, as well as other punctuation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.58
     “
    -0.48
     дописавши
    -0.46
    return
    -0.44
     United
    -0.43
     "
    -0.43
    ях
    -0.43
     Serikat
    -0.43
    stes
    -0.42
    וויק
    -0.42
    POSITIVE LOGITS
    ItemBackground
    0.83
    PullParser
    0.70
     Reſ
    0.70
     Codable
    0.69
    onViewCreated
    0.68
     PhpStorm
    0.68
     Wallflower
    0.68
     useAuth
    0.67
     nargin
    0.66
    lettre
    0.65
    Activations Density 0.265%

    No Known Activations