© 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. 16-GEMMASCOPE-RES-16K
    11. 4852
    Prev
    Next
    INDEX
    Explanations

    phrases indicating purpose or reason

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

    "For" followed by a determiner

    np_acts-logits-general · gemini-2.0-flash

    for + article/reason/purpose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    makeText
    -0.52
    jsoup
    -0.49
    zeiti
    -0.48
    +#+#
    -0.48
    hdessä
    -0.47
     angekommen
    -0.47
     őket
    -0.46
    開催
    -0.45
    édr
    -0.45
    vine
    -0.45
    POSITIVE LOGITS
    RenderAtEndOf
    0.86
     reasons
    0.83
    Personensuche
    0.82
     purposes
    0.76
    reasons
    0.71
    AddTagHelper
    0.71
     Purposes
    0.70
    ագրություններ
    0.69
    purposes
    0.68
    \}_{
    0.68
    Activations Density 0.366%

    No Known Activations