© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2129
    Prev
    Next
    INDEX
    Explanations

    the word "for" and its variations

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

    "for"

    np_acts-logits-general · gemini-2.0-flash

    purpose or recipient

    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
     angekommen
    -0.73
     Cæsar
    -0.69
     Samaria
    -0.63
     Krakowie
    -0.61
     havaianas
    -0.60
     Hadrian
    -0.59
     uchiha
    -0.58
     laikā
    -0.58
     humaines
    -0.58
     raiſ
    -0.57
    POSITIVE LOGITS
     For
    1.26
     FOR
    1.22
     the
    1.17
    FOR
    1.12
    ForValue
    1.00
    For
    0.98
     a
    0.96
    Για
    0.88
    for
    0.86
     for
    0.86
    Activations Density 0.544%

    No Known Activations