© 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. 18-GEMMASCOPE-RES-16K
    11. 358
    Prev
    Next
    INDEX
    Explanations

    terms related to categorization and assessment in research contexts

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

    Lists describing factors, concepts, or items

    np_acts-logits-general · gemini-2.0-flash

    numbers or item counts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vernight
    -0.58
     '\\;'
    -0.55
     otomatig
    -0.53
     unknownFields
    -0.53
    StoryboardSegue
    -0.52
     Италијани
    -0.49
    قایناقلار
    -0.49
    曖昧さ回避
    -0.48
     متحده
    -0.47
     collars
    -0.47
    POSITIVE LOGITS
     list
    0.83
     listed
    0.79
     categories
    0.77
     checklist
    0.71
     core
    0.69
     seven
    0.69
     five
    0.68
     identified
    0.68
     six
    0.68
     interrelated
    0.67
    Activations Density 0.720%

    No Known Activations