Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 7911
    Prev
    Next
    INDEX
    Explanations

    technical terms related to programming, particularly those associated with error messages, package installations, and database management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Python and C-like code

    np_acts-logits-general · gemini-2.0-flash

    python programming

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orija
    -0.50
     Heber
    -0.49
    زار
    -0.49
     Laus
    -0.47
     Peg
    -0.46
    ecuted
    -0.45
    versaries
    -0.45
    fromnode
    -0.44
    ði
    -0.44
    čka
    -0.44
    POSITIVE LOGITS
     Python
    1.01
     python
    0.97
     Py
    0.91
    Python
    0.90
     PYTHON
    0.89
     Anaconda
    0.88
     py
    0.88
     Django
    0.87
    Py
    0.87
    django
    0.85
    Activations Density 0.396%

    No Known Activations