© 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-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 8011
    Prev
    Next
    INDEX
    Explanations

    scientific measurements and classifications related to biological or chemical processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    พร
    -0.55
    ниш
    -0.46
    gel
    -0.44
    PCL
    -0.43
    şil
    -0.42
    drip
    -0.42
    是一種
    -0.42
    ameran
    -0.41
     Anything
    -0.41
     Gel
    -0.41
    POSITIVE LOGITS
     respectively
    2.79
    respectively
    2.38
     respectivamente
    2.26
     respectivement
    1.60
     соответственно
    1.58
     respective
    1.47
     respec
    1.31
     rispet
    1.25
     correspondingly
    1.21
    respective
    1.18
    Activations Density 0.378%

    No Known Activations