© 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. 33-GEMMASCOPE-RES-16K
    11. 295
    Prev
    Next
    INDEX
    Explanations

    instances of structured reasoning and logical progression in arguments or narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     informée
    -0.39
     infine
    -0.35
     впер
    -0.34
     schließlich
    -0.33
    setCellStyle
    -0.32
    今まで
    -0.32
    copg
    -0.32
    </tfoot>
    -0.32
    .*")]
    -0.31
    Filmographie
    -0.31
    POSITIVE LOGITS
     second
    3.03
    second
    2.70
     secondly
    2.61
    Second
    2.47
     Secondly
    2.39
    Secondly
    2.38
     SECOND
    2.38
     Second
    2.34
     segundo
    2.30
     segunda
    2.22
    Activations Density 1.342%

    No Known Activations