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

    Neuronpedia

    Jacobian LensNEW
    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. 18-GEMMASCOPE-RES-16K
    11. 12818
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to medical research findings and statistical significance

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

    "was," "is," or "are" followed by an adjective

    np_acts-logits-general · gemini-2.0-flash

    forms of to be + greatest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Loire
    -0.43
    ma
    -0.41
     upon
    -0.38
    とは
    -0.38
    case
    -0.35
    łec
    -0.35
    OR
    -0.35
    i
    -0.35
    جا
    -0.35
    ま
    -0.35
    POSITIVE LOGITS
     strongest
    1.44
     greatest
    1.40
     heaviest
    1.33
     happiest
    1.33
     loudest
    1.33
    greatest
    1.29
     clearest
    1.21
     easiest
    1.19
     best
    1.18
    pecially
    1.14
    Activations Density 0.606%

    No Known Activations