© 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. 12-GEMMASCOPE-RES-16K
    11. 7014
    Prev
    Next
    INDEX
    Explanations

    phrases that utilize the word "as" 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 @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -1.13
     raiſ
    -1.06
     pleaſure
    -1.01
     Houſe
    -0.97
     ſta
    -0.96
     houſe
    -0.95
     ſever
    -0.94
     Conſ
    -0.94
     Anſ
    -0.93
    ſelf
    -0.93
    POSITIVE LOGITS
     as
    1.21
     As
    1.20
     AS
    1.17
    readAs
    1.05
    As
    1.03
     a
    0.92
     CreateTagHelper
    0.83
     an
    0.82
    as
    0.78
    AS
    0.75
    Activations Density 0.343%

    No Known Activations