© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 1235
    Prev
    Next
    INDEX
    Explanations

    terminology related to pharmacological treatments and clinical contexts involving medications

    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
    ########.
    -0.73
     resourceCulture
    -0.63
    roek
    -0.62
    LayoutStyle
    -0.54
    UVWXYZ
    -0.51
    webElementGuid
    -0.51
    rat
    -0.50
    BeginContext
    -0.49
    BufferException
    -0.47
    InSection
    -0.46
    POSITIVE LOGITS
     re
    3.51
     Re
    3.29
    Re
    3.14
    re
    2.63
     RE
    2.36
    RE
    2.12
     ré
    1.91
     ре
    1.88
     Rew
    1.72
     reo
    1.50
    Activations Density 1.115%

    No Known Activations