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. 6-GEMMASCOPE-RES-16K
    6. 5369
    Prev
    Next
    INDEX
    Explanations

    assertions or claims about conditions and their validity in research or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nyaman
    -0.66
     koos
    -0.63
     zamanda
    -0.62
    ttn
    -0.61
     comodo
    -0.60
     unprotected
    -0.59
     Milan
    -0.59
     evils
    -0.59
    ništvo
    -0.59
    Sized
    -0.59
    POSITIVE LOGITS
     ujednoznacz
    0.69
    ecap
    0.69
     المعرف
    0.60
    เฉ
    0.60
    @",
    0.58
    DoubleQuotes
    0.57
     שוליים
    0.57
    یرات
    0.57
    XmlAccessType
    0.56
     تانيه
    0.56
    Activations Density 0.791%

    No Known Activations