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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 16358
    Prev
    Next
    INDEX
    Explanations

    conjunctions and transitions in discussions

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

    Sentences starting with "And"

    np_acts-logits-general · gemini-2.0-flash

    and followed by a conjunction or pronoun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     متعلقه
    -0.83
    </caption>
    -0.80
    multer
    -0.76
     Efq
    -0.73
    typeorm
    -0.72
    KEYCODE
    -0.71
    />";
    -0.70
    ſelves
    -0.68
    ſelf
    -0.67
     الأخرى
    -0.67
    POSITIVE LOGITS
     it
    1.11
     I
    0.85
     they
    0.82
    それは
    0.81
     therein
    0.79
     eso
    0.78
     there
    0.77
     we
    0.75
     that
    0.74
     rightly
    0.73
    Activations Density 0.264%

    No Known Activations