© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 4783
    Prev
    Next
    INDEX
    Explanations

    code structures and syntax elements, particularly those indicating comments or error handling in programming

    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
     للمعارف
    -1.08
     CreateTagHelper
    -1.01
     doInBackground
    -0.87
    ########.
    -0.85
    NewUrlParser
    -0.85
     виправивши
    -0.84
     ostavi
    -0.84
    ftagPool
    -0.83
    rungsseite
    -0.83
     مشين
    -0.82
    POSITIVE LOGITS
     nothing
    1.35
    nothing
    1.18
    Nothing
    1.15
     Nothing
    1.13
     rien
    0.98
     NOTHING
    0.98
     anything
    0.93
     niets
    0.91
    NOTHING
    0.89
     ничего
    0.87
    Activations Density 0.070%

    No Known Activations