© 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. 1785
    Prev
    Next
    INDEX
    Explanations

    instances of the word "cross" and its variations in various contexts

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

    "crossing" or intersected paths

    np_acts-logits-general · gemini-2.0-flash

    cross over, into, paths, sections

    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
    PhysRevD
    -0.88
    
    -0.87
    ьаж
    -0.79
    Anhalt
    -0.66
    interopRequire
    -0.64
     通販
    -0.62
     réaliste
    -0.61
     بيها
    -0.61
     acheté
    -0.61
     tenuto
    -0.61
    POSITIVE LOGITS
     CROSS
    1.53
     Cross
    1.40
    Cross
    1.40
     crosses
    1.35
    cross
    1.35
     cross
    1.35
    CROSS
    1.33
     crossed
    1.17
    Cros
    1.16
     Crossing
    1.14
    Activations Density 0.079%

    No Known Activations