© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 12209
    Prev
    Next
    INDEX
    Explanations

    references to respect and recognition, particularly towards individuals or groups

    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
    CppMethod
    -0.39
     pozor
    -0.34
    ScopeManager
    -0.32
    AGRAM
    -0.31
     Tand
    -0.29
    DMETHOD
    -0.29
     Doh
    -0.28
     moda
    -0.28
     Ek
    -0.28
    StateList
    -0.28
    POSITIVE LOGITS
     deserve
    2.80
     deserves
    2.66
     deserved
    2.61
     deserving
    2.56
     merit
    2.23
     merits
    2.19
     mérit
    2.17
    deserved
    2.13
     mérite
    2.06
     worthy
    1.95
    Activations Density 0.531%

    No Known Activations