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. 16-GEMMASCOPE-RES-16K
    6. 5264
    Prev
    Next
    INDEX
    Explanations

    references to chemicals and compounds used in scientific experiments

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

    Sourcing or maintenance of cell cultures/animals

    np_acts-logits-general · gemini-2.0-flash

    purchased and maintained

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     урна
    -0.59
    Бахар
    -0.58
     kiệm
    -0.51
    tagHelperRunner
    -0.51
    ReusableCell
    -0.50
     дописавши
    -0.50
    usstsein
    -0.49
     مشين
    -0.47
    csolódó
    -0.47
    tych
    -0.46
    POSITIVE LOGITS
     purity
    0.69
     procured
    0.67
     Purity
    0.60
     supplier
    0.56
    供应商
    0.55
    RRect
    0.55
     purchased
    0.55
     通販
    0.55
     purified
    0.54
     obtained
    0.53
    Activations Density 1.378%

    No Known Activations