© 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. 22-GEMMASCOPE-RES-16K
    6. 12742
    Prev
    Next
    INDEX
    Explanations

    references to legal procedures and evidence in a court context

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

    Comes before verbs like divide, cross, or agree

    np_acts-logits-general · gemini-2.0-flash

    events following specific conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Stays
    -0.90
     Worked
    -0.77
     hears
    -0.75
    RenderAtEndOf
    -0.75
     learns
    -0.74
     stays
    -0.74
     Finds
    -0.74
     Receiving
    -0.73
    Become
    -0.73
     Becomes
    -0.73
    POSITIVE LOGITS
     devriez
    0.58
     murni
    0.55
     iż
    0.52
     infine
    0.49
     respectivas
    0.48
     fleste
    0.47
     récentes
    0.47
     supuestamente
    0.47
     inflación
    0.47
     endast
    0.47
    Activations Density 1.758%

    No Known Activations