Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 19-GEMMASCOPE-RES-16K
    6. 15756
    Prev
    Next
    INDEX
    Explanations

    future tense verbs and expressions indicating likelihood or certainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    férences
    -0.63
     Exacts
    -0.60
    xtick
    -0.60
    parsedMessage
    -0.59
    DoubleQuotes
    -0.54
     μην
    -0.54
    ाहरण
    -0.54
     Fuchs
    -0.54
    置信
    -0.54
    GEBURTSDATUM
    -0.53
    POSITIVE LOGITS
     surely
    0.89
     likely
    0.88
     undoubtedly
    0.87
     sicuramente
    0.87
     definitely
    0.85
    fully
    0.85
     certainly
    0.85
     doubtless
    0.84
     probably
    0.81
     soon
    0.80
    Activations Density 0.216%

    No Known Activations