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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 16-GEMMASCOPE-RES-16K
    6. 12488
    Prev
    Next
    INDEX
    Explanations

    plural third-person verbs and specific human or ecological conditions

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

    Followed by verbs

    np_acts-logits-general · gemini-2.0-flash

    because following common verbs

    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
     however
    -0.65
     daher
    -0.59
     tuttavia
    -0.58
     übrigens
    -0.57
    however
    -0.57
     inoltre
    -0.56
     entanto
    -0.56
     imidlertid
    -0.52
     конечно
    -0.49
     cependant
    -0.49
    POSITIVE LOGITS
    NUMX
    0.78
    ThroughAttribute
    0.77
    "]];
    0.77
     przecież
    0.76
     ostavi
    0.70
    Хьажоргаш
    0.68
    بوابة
    0.68
     InputDecoration
    0.67
    畢竟
    0.66
    ]";
    0.65
    Activations Density 0.394%

    No Known Activations