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. 12-GEMMASCOPE-RES-16K
    6. 11661
    Prev
    Next
    INDEX
    Explanations

    patterns and specific values in structured data, likely related to numerical or categorical information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Rohy
    -0.64
    mybatisplus
    -0.62
    XmlAccessType
    -0.60
    mergeFrom
    -0.58
    illaume
    -0.57
    principalColumn
    -0.56
    libft
    -0.52
     actionMode
    -0.52
    AfterClass
    -0.52
     kazan
    -0.51
    POSITIVE LOGITS
    Composable
    0.73
    expandindo
    0.70
    wikidata
    0.68
    awaiter
    0.66
    prnewswire
    0.66
    ̈́
    0.64
    الدراسه
    0.63
    sedown
    0.62
     وتسجيلات
    0.60
    PerformLayout
    0.60
    Activations Density 0.060%

    No Known Activations