© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 2469
    Prev
    Next
    INDEX
    Explanations

    references to organizational support and collaborative efforts in research and fundraising

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

    "Already" and its translations/forms

    np_acts-logits-general · gemini-2.0-flash

    already / déjà

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     altijd
    -0.76
    ALWAYS
    -0.70
     همیشه
    -0.69
     always
    -0.67
     siempre
    -0.67
     sempre
    -0.66
    Always
    -0.66
    Years
    -0.65
     annually
    -0.65
    always
    -0.64
    POSITIVE LOGITS
     already
    1.87
     Already
    1.80
    Already
    1.79
    already
    1.73
     ALREADY
    1.49
     allerede
    1.30
    早速
    1.25
     déjà
    1.23
    さっそく
    1.19
    すでに
    1.18
    Activations Density 0.376%

    No Known Activations