Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 602
    Prev
    Next
    INDEX
    Explanations

    abbreviations and specific notation used in scientific or technical documents

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

    Mathematical or chemical formulas

    np_acts-logits-general · gemini-2.0-flash

    mathematical notation and equations

    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
     mergeFrom
    -0.67
    ↵↵
    -0.59
    ges
    -0.54
     пара
    -0.53
     средств
    -0.53
     bas
    -0.52
     --
    -0.51
    readString
    -0.51
    ="/
    -0.50
     <",
    -0.49
    POSITIVE LOGITS
     GenerationType
    0.89
    VersionUID
    0.79
     Wikiseite
    0.79
    trường
    0.77
     pymongo
    0.77
     Numbers
    0.76
    mn
    0.76
     كومونز
    0.74
     للمعارف
    0.73
     NSCoder
    0.72
    Activations Density 0.020%

    No Known Activations