© 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. 23-GEMMASCOPE-RES-16K
    11. 9268
    Prev
    Next
    INDEX
    Explanations

    phrases indicating authority and official roles within organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.57
    EDEFAULT
    -0.55
    __*/
    -0.49
    UrlResolution
    -0.45
    });*/
    -0.44
     OMITBAD
    -0.44
    Nazionale
    -0.44
     INTERESAR
    -0.42
    Naissance
    -0.42
    MemoryWarning
    -0.41
    POSITIVE LOGITS
     OFDb
    0.45
     kemudian
    0.42
    evos
    0.40
     then
    0.38
     затем
    0.37
     quickly
    0.36
     nurtured
    0.36
     subsequent
    0.35
     later
    0.35
     continues
    0.35
    Activations Density 0.623%

    No Known Activations