© 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. 4-GEMMASCOPE-RES-16K
    11. 11560
    Prev
    Next
    INDEX
    Explanations

    instances of the word "space" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    @[+][
    -0.88
     Monfieur
    -0.86
     proprement
    -0.86
     zelve
    -0.85
    quelles
    -0.82
     aveug
    -0.82
    __":
    -0.82
     hydrauli
    -0.81
     ainfi
    -0.81
     themſelves
    -0.81
    POSITIVE LOGITS
     space
    2.65
     Space
    2.44
     spaces
    2.42
    space
    2.38
     SPACE
    2.34
    Space
    2.29
     Spaces
    2.20
    SPACE
    2.19
    Spaces
    2.15
    spaces
    2.10
    Activations Density 0.036%

    No Known Activations