© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 27-GEMMASCOPE-RES-16K
    11. 9915
    Prev
    Next
    INDEX
    Explanations

    assignments in programming code, particularly in loops and conditional statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    featureID
    -0.80
     lenker
    -0.78
    évaluateur
    -0.77
    richTextPanel
    -0.75
    GEBURTSDATUM
    -0.72
     препратки
    -0.70
    __*/
    -0.65
     disambiguazione
    -0.63
     Италијани
    -0.63
     مشين
    -0.63
    POSITIVE LOGITS
     quieras
    0.35
     librement
    0.35
     beginning
    0.34
     terlaris
    0.34
     inférieure
    0.34
     libremente
    0.33
     pokok
    0.32
     izvē
    0.32
     empez
    0.32
     mukana
    0.32
    Activations Density 0.120%

    No Known Activations