Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-GEMMASCOPE-RES-16K
    6. 1791
    Prev
    Next
    INDEX
    Explanations

    occurrences and variations of the word "count" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ?\\
    -0.71
    ¹)
    -0.65
    HomeScreen
    -0.64
     ApiService
    -0.63
    }}$\\
    -0.63
     userEmail
    -0.63
     pObj
    -0.63
     Pexels
    -0.62
    Geplaatst
    -0.61
    ///
    
    -0.61
    POSITIVE LOGITS
     COUNT
    1.35
     counts
    1.34
    count
    1.28
     count
    1.26
    counts
    1.25
    COUNT
    1.24
     Count
    1.23
     counted
    1.22
     Counts
    1.19
     Counting
    1.13
    Activations Density 0.053%

    No Known Activations