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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-GEMMASCOPE-RES-16K
    6. 13262
    Prev
    Next
    INDEX
    Explanations

    terms and questions related to mathematical concepts, particularly those focusing on greatest common factors or divisors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CURIAM
    -0.57
    __':
    -0.56
    픈
    -0.53
     hagas
    -0.51
     religieuses
    -0.51
     vayan
    -0.50
    ąp
    -0.50
     godine
    -0.50
    はじめに
    -0.50
     russes
    -0.48
    POSITIVE LOGITS
    OGND
    0.78
    LookAnd
    0.72
     חיצוניים
    0.72
    ollectionView
    0.61
     تانيه
    0.61
    الإنجليزية
    0.61
    ]--;
    0.60
    ')")
    0.60
    èdia
    0.59
    ]]);
    0.59
    Activations Density 0.316%

    No Known Activations