© 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. 11-GEMMASCOPE-RES-16K
    6. 13351
    Prev
    Next
    INDEX
    Explanations

    occurrences of the Python `__name__` variable and its comparison to denote the main entry point of a script

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    webElement
    -0.60
    flink
    -0.58
    awtextra
    -0.55
    тисти
    -0.53
     Zas
    -0.52
    thâu
    -0.50
    '],$
    -0.49
    Хьажоргаш
    -0.49
     مرئيه
    -0.47
    ('|
    -0.46
    POSITIVE LOGITS
    __':
    
    0.96
    __':
    0.84
    __":
    
    0.83
    __":
    0.71
    tadiene
    0.70
     ExecuteAsync
    0.60
    quinone
    0.60
    RelativeTo
    0.59
    mobileqq
    0.59
    onAttach
    0.58
    Activations Density 0.026%

    No Known Activations