© 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. 25-GEMMASCOPE-RES-16K
    11. 15870
    Prev
    Next
    INDEX
    Explanations

    instances of the word "made" along with variations indicating creation, availability, or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 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
     ponts
    -0.28
    ırken
    -0.27
     ε
    -0.27
    פון
    -0.27
     lẫn
    -0.27
     у
    -0.26
     cri
    -0.26
     pl
    -0.25
    .
    -0.25
     ,
    -0.25
    POSITIVE LOGITS
    CreateModel
    0.75
    webElement
    0.69
    featureID
    0.69
    Hochspringen
    0.66
    ðsíða
    0.65
    majánló
    0.65
     oprot
    0.64
    writeField
    0.64
    prepareStatement
    0.63
     nakalista
    0.63
    Activations Density 0.315%

    No Known Activations