© 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. 16-GEMMASCOPE-RES-16K
    11. 4914
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate specific conditions or circumstances when something occurs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "when"

    np_acts-logits-general · gemini-2.0-flash

    when it comes to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     purpoſe
    -0.95
     himſelf
    -0.85
     ſtate
    -0.84
     houſe
    -0.80
     ſame
    -0.76
     Jefus
    -0.76
     rodríguez
    -0.73
     auroit
    -0.73
     ſy
    -0.72
     Majefty
    -0.71
    POSITIVE LOGITS
     when
    1.09
     WHEN
    1.01
     When
    0.99
    when
    0.98
    WHEN
    0.93
    When
    0.91
     they
    0.88
     we
    0.84
     när
    0.82
    cuando
    0.78
    Activations Density 0.102%

    No Known Activations