© 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. 5-GEMMASCOPE-RES-16K
    11. 8239
    Prev
    Next
    INDEX
    Explanations

    timestamps and numerical data, particularly relating to dates and times

    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
    ony
    -0.43
    propTypes
    -0.43
     Ren
    -0.39
    ưởng
    -0.39
     forme
    -0.38
    uchen
    -0.37
     ad
    -0.37
    Lengths
    -0.36
     ges
    -0.36
    klar
    -0.36
    POSITIVE LOGITS
    sidemargin
    1.03
     CreateTagHelper
    1.00
    MessageOf
    0.87
    تقاوى
    0.86
     GenerationType
    0.85
    IntoConstraints
    0.81
     Baillargeon
    0.80
    UnusedPrivate
    0.77
     myſelf
    0.76
     otomatig
    0.76
    Activations Density 0.324%

    No Known Activations