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. 1020
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming and software development

    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
    zent
    -0.52
     when
    -0.48
    when
    -0.46
    regarding
    -0.46
    zer
    -0.46
    리
    -0.46
    odu
    -0.45
    imenti
    -0.45
    }^{-}\
    -0.44
    ございます
    -0.44
    POSITIVE LOGITS
     static
    2.34
    static
    2.11
    静态
    1.36
     STATIC
    1.35
    Static
    1.31
     Static
    1.30
    staticmethod
    1.19
    STATIC
    1.18
     静
    1.03
    classmethod
    0.97
    Activations Density 0.071%

    No Known Activations