© 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. 23-GEMMASCOPE-RES-16K
    11. 13130
    Prev
    Next
    INDEX
    Explanations

    words that contain the letters "sp" or are related to spatial concepts and themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    specification
    -0.70
     specification
    -0.65
     spec
    -0.64
    specified
    -0.63
    specify
    -0.62
     specify
    -0.59
     specified
    -0.59
    aspect
    -0.56
     Спе
    -0.55
    Specification
    -0.55
    POSITIVE LOGITS
     springfox
    0.71
    /**
    0.68
    afficheront
    0.65
     comerciais
    0.59
    󠁧
    0.59
     Agnew
    0.58
     deose
    0.58
    aneous
    0.58
    tacular
    0.57
     页
    0.57
    Activations Density 0.320%

    No Known Activations