© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 14897
    Prev
    Next
    INDEX
    Explanations

    references to specific substances, particularly related to medical or scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     enquiry
    -0.58
     beetroot
    -0.58
     Palae
    -0.57
     yoghurt
    -0.55
     Maths
    -0.54
     Enquiry
    -0.53
     aeroplane
    -0.53
    MockBean
    -0.53
     metre
    -0.52
     spoilt
    -0.51
    POSITIVE LOGITS
     Larson
    0.73
    ſelf
    0.71
    Stacy
    0.71
     Callahan
    0.66
     Stacy
    0.65
     Schuyler
    0.64
    hitheater
    0.64
    __*/
    0.64
     Theater
    0.63
    ency
    0.63
    Activations Density 3.475%

    No Known Activations