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. 25-GEMMASCOPE-RES-16K
    6. 12516
    Prev
    Next
    INDEX
    Explanations

    references to societal issues, particularly relating to real estate and community dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awaiter
    -0.57
     mapStateToProps
    -0.51
     contextLoads
    -0.51
    matchCondition
    -0.51
     pageIndex
    -0.44
     allowances
    -0.43
    الة
    -0.42
    anterior
    -0.42
     allowance
    -0.42
    وشی
    -0.42
    POSITIVE LOGITS
     للاسماء
    0.76
     defaultstate
    0.62
    mybatisplus
    0.59
     Мексичка
    0.55
    ValueStyle
    0.52
    elemField
    0.52
     Italijani
    0.51
    yntaxException
    0.50
    StructEnd
    0.50
    Appropriate
    0.50
    Activations Density 0.180%

    No Known Activations