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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 10841
    Prev
    Next
    INDEX
    Explanations

    specific terminology related to healthcare and medical contexts

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

    ending with "ing", "ed", "ae", "ion", or "er"

    np_acts-logits-general · gemini-2.0-flash

    scientific and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ers
    -0.56
    an
    -0.55
    makeConstraints
    -0.54
    ency
    -0.53
     StringTokenizer
    -0.50
    u
    -0.48
    ufig
    -0.47
    anor
    -0.47
    __*/
    -0.47
    logic
    -0.47
    POSITIVE LOGITS
     optimised
    0.56
     randomised
    0.54
     fertiliser
    0.53
     utilising
    0.52
     watercolour
    0.52
    paedia
    0.51
     jewellery
    0.51
     schli
    0.50
     yoghurt
    0.50
     utilisation
    0.50
    Activations Density 2.812%

    No Known Activations