© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 4711
    Prev
    Next
    INDEX
    Explanations

    the beginning of a new section or document, marked by the token <bos>

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InSection
    -0.91
     AssemblyProduct
    -0.85
    verifyException
    -0.84
    SOUNDBITE
    -0.81
    sizeCache
    -0.79
     nahilalakip
    -0.76
    IsContent
    -0.75
    NameInMap
    -0.74
    urlpatterns
    -0.73
    AndEndTag
    -0.73
    POSITIVE LOGITS
    TagHelpers
    0.80
    TagHelper
    0.54
     eds
    0.51
     the
    0.50
    excellents
    0.46
    lah
    0.44
    ibatis
    0.44
     déroule
    0.44
     تضيفلها
    0.44
    TIMORE
    0.43
    Activations Density 0.006%

    No Known Activations