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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 44111
    Prev
    Next
    INDEX
    Explanations

    specific coding structures or comments in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    isContained
    -0.73
     queſta
    -0.71
    andExpect
    -0.71
    ésultats
    -0.69
     témoig
    -0.68
     dezelve
    -0.68
     zoude
    -0.67
    VYMaps
    -0.64
     queſto
    -0.64
     zijne
    -0.64
    POSITIVE LOGITS
    .*")]
    0.34
    ↵
    0.34
    ↵↵↵
    0.33
    Рис
    0.31
    ↵↵↵↵↵
    0.30
    root
    0.29
    ]));
    0.29
    SOUNDBITE
    0.29
    complexContent
    0.29
    ↵↵↵↵
    0.29
    Activations Density 0.005%

    No Known Activations