© 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. 1-GEMMASCOPE-RES-16K
    11. 8986
    Prev
    Next
    INDEX
    Explanations

    the repeated use of the verb "are" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    printLine
    -0.65
     then
    -0.64
     was
    -0.63
     finally
    -0.62
    uzzi
    -0.60
     never
    -0.55
    ITHER
    -0.55
     ca
    -0.54
     co
    -0.53
    phosa
    -0.52
    POSITIVE LOGITS
    are
    1.36
    have
    1.15
    can
    1.02
    has
    1.01
    will
    1.00
     itſelf
    0.98
    was
    0.95
     themſelves
    0.90
    were
    0.89
     myſelf
    0.85
    Activations Density 0.104%

    No Known Activations