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. 2-GEMMASCOPE-RES-16K
    6. 4277
    Prev
    Next
    INDEX
    Explanations

    numerical data or references to court cases and legal details

    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
    tvguidetime
    -0.80
    GraphicsUnit
    -0.74
    useNewUrlParser
    -0.69
     EnglishChoose
    -0.67
    LikeLiked
    -0.67
    setViewportView
    -0.65
     iesp
    -0.65
    Glej
    -0.63
    resave
    -0.63
    mappedBy
    -0.62
    POSITIVE LOGITS
    󠁿
    1.16
    ">(</
    0.66
     سكانية
    0.63
    thâu
    0.59
    enderror
    0.58
    Personensuche
    0.58
    ześnie
    0.56
    μβρίου
    0.56
    üyada
    0.55
    ☸
    0.52
    Activations Density 1.768%

    No Known Activations