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. 21-GEMMASCOPE-RES-16K
    6. 848
    Prev
    Next
    INDEX
    Explanations

    components related to coding functions and class structures

    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
    AndroidJUnit
    -0.70
    تقاوى
    -0.62
    iast
    -0.59
     ErrIntOverflow
    -0.56
    protoimpl
    -0.53
    EnableWeb
    -0.53
     réguli
    -0.53
    adə
    -0.52
     énergé
    -0.52
     sumpay
    -0.50
    POSITIVE LOGITS
    исленность
    0.63
    typeorm
    0.55
    TagMode
    0.52
    RegressionTest
    0.51
    ]}>
    0.51
     الحره
    0.49
    findpost
    0.49
    లాలు
    0.49
     AspNetCore
    0.48
    }\]
    0.47
    Activations Density 0.018%

    No Known Activations