© 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. 15-GEMMASCOPE-RES-16K
    11. 12575
    Prev
    Next
    INDEX
    Explanations

    the word "for" and related phrases indicating purpose or reason

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iada
    -0.55
    ışı
    -0.54
     cortesía
    -0.52
    withIdentifier
    -0.50
    انتهای
    -0.49
    voorbeeld
    -0.49
    ardin
    -0.49
     Hotspur
    -0.49
     casco
    -0.48
     thang
    -0.48
    POSITIVE LOGITS
     there
    1.05
    there
    0.81
     they
    0.80
     Sebab
    0.74
     Ведь
    0.72
    Ведь
    0.68
     we
    0.67
     THERE
    0.65
     although
    0.65
     it
    0.65
    Activations Density 0.185%

    No Known Activations