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. 20-GEMMASCOPE-RES-16K
    6. 5224
    Prev
    Next
    INDEX
    Explanations

    programmatic syntax elements and structures in code

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

    Starts with an underscore

    np_acts-logits-general · gemini-2.0-flash

    _storage member access

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    {}'.
    -0.92
    {}".
    -0.88
    ]").
    -0.79
    grà
    -0.72
    ']")
    -0.71
    __).
    -0.69
    "}>
    -0.68
    "){
    
    -0.67
    OGND
    -0.67
    )";
    
    -0.65
    POSITIVE LOGITS
    jspx
    0.83
    ._
    0.65
    ::_
    0.62
    ->_
    0.62
     bancaria
    0.61
     mosso
    0.59
    =_
    0.58
     privata
    0.56
     Myra
    0.56
    afone
    0.55
    Activations Density 0.113%

    No Known Activations