© 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. 23-GEMMASCOPE-RES-16K
    11. 1805
    Prev
    Next
    INDEX
    Explanations

    instances of the word "often" and its variations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 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
    IntoConstraints
    -0.62
     NM
    -0.52
     isole
    -0.51
    odiment
    -0.51
    anzug
    -0.47
    deinit
    -0.47
    瘩
    -0.46
    InjectMocks
    -0.46
     Schild
    -0.46
     Shiro
    -0.45
    POSITIVE LOGITS
     often
    0.79
    often
    0.75
    Often
    0.74
    frequently
    0.73
     frequently
    0.70
     Often
    0.70
     frecuencia
    0.64
     kerap
    0.63
     často
    0.63
     frequentemente
    0.63
    Activations Density 0.077%

    No Known Activations