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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 39126
    Prev
    Next
    INDEX
    Explanations

    programming syntax and structure, particularly function calls and variable assignments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estimés
    -0.62
    ')['
    -0.56
    )?;
    -0.56
    ]');
    -0.56
    Composable
    -0.50
    )$/,
    -0.50
    Mga
    -0.48
    はじめに
    -0.48
    Ens
    -0.47
    )++;
    -0.47
    POSITIVE LOGITS
    ConstraintMaker
    0.73
     propOrder
    0.70
    #+#
    0.67
    TestingModule
    0.64
     ویکی‌پدیای
    0.58
     Majefty
    0.57
     TextAppearance
    0.57
     kaarangay
    0.56
    getJSONArray
    0.56
     défaut
    0.54
    Activations Density 0.029%

    No Known Activations