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. 835
    Prev
    Next
    INDEX
    Explanations

    technical terms related to programming and API functionality

    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
     himself
    -1.76
     his
    -1.47
    himself
    -1.34
    his
    -1.32
     Himself
    -1.19
    彼は
    -1.06
    彼の
    -1.06
    His
    -1.04
     koji
    -1.03
     seine
    -1.03
    POSITIVE LOGITS
     herself
    1.80
    herself
    1.16
     she
    1.13
     која
    1.06
     koja
    1.04
     która
    0.97
     internetowa
    0.87
     ihrem
    0.85
     her
    0.84
     которая
    0.83
    Activations Density 0.179%

    No Known Activations