Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 25-GEMMASCOPE-RES-16K
    6. 12556
    Prev
    Next
    INDEX
    Explanations

    terms related to healthcare, medical accuracy, and patient-provider communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.69
     mxArray
    -0.62
     utafitiHapana
    -0.59
     actionTypes
    -0.59
    CodedInputStream
    -0.57
    <?
    -0.56
    了出来
    -0.55
    SequentialGroup
    -0.55
     nemlig
    -0.54
    "]));
    -0.54
    POSITIVE LOGITS
     or
    4.14
     или
    2.94
    或
    2.65
     atau
    2.61
     eller
    2.54
    或者
    2.49
     یا
    2.44
     hoặc
    2.43
     nebo
    2.37
    หรือ
    2.36
    Activations Density 5.724%

    No Known Activations