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. 15-GEMMASCOPE-RES-16K
    6. 8487
    Prev
    Next
    INDEX
    Explanations

    references to conspiracies involving extraterrestrial beings or malevolent entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ArrowToggle
    -0.69
     Roskov
    -0.64
     ivelany
    -0.63
     становника
    -0.63
    seamnă
    -0.63
     sherds
    -0.61
    weetened
    -0.60
    EndContext
    -0.60
    Viitteet
    -0.60
    CppMethod
    -0.58
    POSITIVE LOGITS
     alleged
    0.84
     UFO
    0.69
    HtmlAttribute
    0.69
     paranormal
    0.68
     allegedly
    0.68
     paran
    0.67
     secret
    0.67
    UFO
    0.65
     unexplained
    0.62
     mysterious
    0.61
    Activations Density 0.572%

    No Known Activations