© 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. 15-GEMMASCOPE-RES-16K
    11. 8184
    Prev
    Next
    INDEX
    Explanations

    specific terms related to types of media, specifically comics or cartoons

    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
    AndEndTag
    -0.71
    تفصیلات
    -0.65
    WithIOException
    -0.60
    sidemargin
    -0.59
    Hun
    -0.52
     contributors
    -0.52
    StatusCode
    -0.52
     anthrop
    -0.52
    uchungen
    -0.51
    styleType
    -0.51
    POSITIVE LOGITS
     split
    1.13
     twin
    1.08
     splitting
    1.05
     twins
    1.05
     doppia
    1.02
     double
    1.02
     dual
    1.01
     two
    1.00
    split
    0.98
     pair
    0.98
    Activations Density 0.931%

    No Known Activations