© 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. 2-GEMMASCOPE-RES-16K
    11. 3538
    Prev
    Next
    INDEX
    Explanations

    intensifiers, particularly the word "very," indicating a strong emphasis or degree in descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CURIAM
    -0.60
     ſche
    -0.52
    exitRule
    -0.51
     cauſe
    -0.49
     defaultstate
    -0.48
     purpoſe
    -0.48
     ſtate
    -0.48
     juſ
    -0.47
    neſs
    -0.47
    leſs
    -0.47
    POSITIVE LOGITS
     very
    3.91
    Very
    3.25
    very
    3.20
     Very
    3.19
     VERY
    2.86
    VERY
    2.64
     très
    2.63
     muy
    2.63
     sehr
    2.52
     очень
    2.45
    Activations Density 0.090%

    No Known Activations