© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 5120
    Prev
    Next
    INDEX
    Explanations

    references to levels or degrees of measurement

    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
    izop
    -0.77
    Dum
    -0.69
     muzik
    -0.67
    ystis
    -0.65
     Selby
    -0.65
     Dum
    -0.65
     Vand
    -0.63
    vist
    -0.63
     giovan
    -0.63
    BoxLayout
    -0.62
    POSITIVE LOGITS
     degree
    2.28
     degrees
    2.23
     Degree
    2.12
     Degrees
    2.08
    degree
    2.03
    Degree
    2.02
     DEGREE
    1.99
    degrees
    1.87
    Degrees
    1.84
     degré
    1.55
    Activations Density 0.094%

    No Known Activations