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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 21-GEMMASCOPE-RES-16K
    6. 482
    Prev
    Next
    INDEX
    Explanations

    combinations or patterns of punctuation and conjunctions in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     doubtnut
    -1.34
     itſelf
    -1.31
     myſelf
    -1.25
     ―――――
    -1.24
     ་་
    -1.20
     photolibrary
    -1.16
     betweenstory
    -1.16
    ſelf
    -1.16
     NSCoder
    -1.13
    ſelves
    -1.13
    POSITIVE LOGITS
     we
    1.12
    <eos>
    1.05
    ↵
    1.05
    ↵↵
    1.02
     
    1.01
     I
    0.97
     you
    0.92
     they
    0.89
    we
    0.88
     he
    0.86
    Activations Density 0.970%

    No Known Activations