© 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. 9-GEMMASCOPE-RES-16K
    11. 717
    Prev
    Next
    INDEX
    Explanations

    phrases indicating necessity or requirements in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.98
    клопе
    -0.97
     تانيه
    -0.94
    WebVitals
    -0.90
     EconPapers
    -0.90
    UrlResolution
    -0.84
     propOrder
    -0.83
     tartalomajánló
    -0.81
    setVerticalGroup
    -0.81
    AddTagHelper
    -0.78
    POSITIVE LOGITS
     said
    0.53
    sinx
    0.46
     warned
    0.44
     laughed
    0.43
     appealed
    0.42
    ALSO
    0.42
     gril
    0.42
     angered
    0.42
     gripped
    0.41
    haven
    0.40
    Activations Density 1.148%

    No Known Activations