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. 12-GEMMASCOPE-RES-16K
    6. 10069
    Prev
    Next
    INDEX
    Explanations

    instances of the word "too" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setDisabled
    -0.50
    rat
    -0.50
     offene
    -0.50
    ],
    
    -0.48
     singola
    -0.48
     plugs
    -0.47
     réglable
    -0.47
    кот
    -0.47
    eno
    -0.47
    ын
    -0.47
    POSITIVE LOGITS
    saraba
    0.90
    MLLoader
    0.87
    帖最后由
    0.87
     Paglinawan
    0.86
    FunctionFlags
    0.85
    tanleria
    0.85
     oprot
    0.83
    DockStyle
    0.82
    enumi
    0.81
     Wikimedijinoj
    0.81
    Activations Density 0.142%

    No Known Activations