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. 6-GEMMASCOPE-RES-16K
    6. 11973
    Prev
    Next
    INDEX
    Explanations

    the presence of specific formatting or special tokens in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -1.09
     disambiguazione
    -0.82
     فريبيس
    -0.80
    ValueStyle
    -0.80
    Datuak
    -0.79
     ویکی‌پدیای
    -0.79
    DeleteBehavior
    -0.79
     الرياضيه
    -0.73
    Expedia
    -0.72
     Biôgrafia
    -0.71
    POSITIVE LOGITS
    VersionUID
    0.59
     namorado
    0.53
     chapéu
    0.51
    Atoi
    0.51
     traded
    0.48
     clasificación
    0.48
     Behav
    0.48
     Zweiten
    0.47
     Bellini
    0.46
    :///
    0.46
    Activations Density 0.014%

    No Known Activations