© 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. 23-GEMMASCOPE-RES-16K
    11. 9774
    Prev
    Next
    INDEX
    Explanations

    structural elements of code, specifically function definitions and calls

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 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
    #+#
    -0.77
    TypedDataSet
    -0.70
    VIAF
    -0.63
    __":
    -0.61
    makeConstraints
    -0.61
    }],
    -0.58
    Portail
    -0.57
     Италијани
    -0.56
    __':
    -0.56
    viewDidLoad
    -0.55
    POSITIVE LOGITS
    if
    2.83
     if
    2.82
     If
    2.02
     jika
    1.96
    If
    1.96
     если
    1.92
     dacă
    1.91
     nếu
    1.86
     hvis
    1.70
     اگر
    1.70
    Activations Density 0.201%

    No Known Activations