© 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. 22-GEMMASCOPE-RES-16K
    11. 8090
    Prev
    Next
    INDEX
    Explanations

    mentions of "the" in various contexts, indicating a focus on specific subjects or entities in the text

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

    followed by adjectives

    np_acts-logits-general · gemini-2.0-flash

    the primary subject

    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
    thâu
    -0.91
    GEBURTSDATUM
    -0.91
     lenker
    -0.87
     سكانية
    -0.87
     however
    -0.87
     pleaſure
    -0.87
     Мексичка
    -0.87
     дописавши
    -0.85
    Datuak
    -0.85
    WebServlet
    -0.84
    POSITIVE LOGITS
     brand
    0.67
     primary
    0.64
    brand
    0.59
     Brand
    0.56
     identical
    0.52
     truth
    0.51
    Brand
    0.51
    primary
    0.51
     BRAND
    0.51
     opposite
    0.50
    Activations Density 0.075%

    No Known Activations