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. 20-GEMMASCOPE-RES-16K
    6. 7739
    Prev
    Next
    INDEX
    Explanations

    formatted data structures and syntax used in programming code

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

    Code snippets or code-related terms

    np_acts-logits-general · gemini-2.0-flash

    code syntax and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AB
    -0.51
    ueba
    -0.49
     tumble
    -0.48
     sur
    -0.48
     shot
    -0.47
     off
    -0.47
    Życiorys
    -0.47
     CYTHON
    -0.46
     pos
    -0.46
     συν
    -0.44
    POSITIVE LOGITS
    
    0.76
     nakalista
    0.73
    UserScript
    0.72
    Referanser
    0.72
    parsedMessage
    0.71
    BufferException
    0.68
     ſche
    0.66
     plagio
    0.65
    存于互联网档案馆
    0.64
    Hozzáférés
    0.64
    Activations Density 0.049%

    No Known Activations