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 - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 4286
    Prev
    Next
    INDEX
    Explanations

    file paths or references that denote resources or links in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pinulongan
    -0.74
     defaultstate
    -0.65
    aarrggbb
    -0.62
    رشف
    -0.58
     météo
    -0.49
    classnames
    -0.49
    ExecuteReader
    -0.48
    DoubleQuotes
    -0.48
     détaillée
    -0.47
    AutoresizingMask
    -0.47
    POSITIVE LOGITS
    TagMode
    1.75
     disambiguazione
    0.64
     makeStyles
    0.57
    djangoproject
    0.56
    <bos>
    0.56
    IMPORTED
    0.55
     DPR
    0.52
    ="@+
    0.52
    autoreleasepool
    0.51
    });*/
    0.51
    Activations Density 0.010%

    No Known Activations