© 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. 4-GEMMASCOPE-RES-16K
    11. 2333
    Prev
    Next
    INDEX
    Explanations

    elements of programming syntax, specifically related to variable declarations and assignments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ceğini
    -0.47
     RE
    -0.46
     OMIT
    -0.45
     Re
    -0.44
    edict
    -0.43
    Aktualisiert
    -0.42
     im
    -0.39
     $\
    -0.39
     reban
    -0.39
     Im
    -0.39
    POSITIVE LOGITS
     pleaſure
    0.98
     houſe
    0.96
     Monfieur
    0.92
     ſtate
    0.91
     cauſe
    0.91
     Houſe
    0.91
     Anſ
    0.84
     kasarigan
    0.84
     purpoſe
    0.84
     ſtre
    0.83
    Activations Density 0.210%

    No Known Activations