© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9890
    Prev
    Next
    INDEX
    Explanations

    elements related to combat mechanics and game messaging systems

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

    Code, scripting, or programming-related terms

    np_acts-logits-general · gemini-2.0-flash

    gaming, technical, special characters

    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
     '\\;'
    -0.53
    substack
    -0.46
     magasiner
    -0.45
     tardi
    -0.45
     Unito
    -0.43
    çoise
    -0.42
    ьаж
    -0.41
     hinaus
    -0.41
    Viitteet
    -0.40
     rejet
    -0.40
    POSITIVE LOGITS
    cookieParser
    0.67
     mergeFrom
    0.64
     ModelExpression
    0.64
     समीक्षाओं
    0.63
    XmlAccessType
    0.62
    Попис
    0.60
     guild
    0.59
     NPC
    0.58
     afk
    0.57
     raids
    0.57
    Activations Density 0.289%

    No Known Activations