© 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-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 3547
    Prev
    Next
    INDEX
    Explanations

    the presence of various coding constructs and structures typical in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    subpackage
    -0.61
     Erl
    -0.55
    writerow
    -0.54
    menn
    -0.51
     createSlice
    -0.50
     MediaType
    -0.48
    otheby
    -0.47
    kol
    -0.47
     press
    -0.47
    략
    -0.46
    POSITIVE LOGITS
     mergeFrom
    0.69
    delwed
    0.61
    ︎
    0.60
     <=",
    0.58
    webElementGuid
    0.58
     Tagore
    0.57
    visionnement
    0.55
    rizona
    0.53
    Alike
    0.53
    /**
    0.52
    Activations Density 0.151%

    No Known Activations