© 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-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 2162
    Prev
    Next
    INDEX
    Explanations

    references to specific characters or themes in a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 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
    iat
    -0.66
    iate
    -0.58
    hong
    -0.58
    ised
    -0.57
    hua
    -0.57
    zhen
    -0.57
    zhong
    -0.56
    aaa
    -0.56
    iw
    -0.56
    iy
    -0.55
    POSITIVE LOGITS
    ConstraintMaker
    0.62
    in
    0.60
    u
    0.52
    SPJ
    0.50
     referrerpolicy
    0.50
    s
    0.45
     poveznice
    0.45
     estimés
    0.44
    suit
    0.44
    MemoryWarning
    0.43
    Activations Density 0.349%

    No Known Activations