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. 5-GEMMASCOPE-RES-16K
    6. 12918
    Prev
    Next
    INDEX
    Explanations

    instances of the word "called" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     незавершена
    -0.57
     '.';
    -0.53
     disambiguazione
    -0.52
     prochains
    -0.50
     traseiro
    -0.49
     Expl
    -0.48
     Stande
    -0.48
    δρ
    -0.48
    ின
    -0.47
     '-';
    -0.47
    POSITIVE LOGITS
     called
    1.64
    called
    1.50
     CALLED
    1.44
     Called
    1.43
    Called
    1.33
     llamado
    1.28
     chamado
    1.17
     bernama
    1.13
    叫做
    1.12
     named
    1.08
    Activations Density 0.099%

    No Known Activations