© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 9455
    Prev
    Next
    INDEX
    Explanations

    references to databases or indexes related to authoritative information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/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.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     بيها
    -0.56
     CURIAM
    -0.56
    onAttach
    -0.54
    ///</
    -0.52
     initComponents
    -0.51
    __*/
    -0.51
    RectangleBorder
    -0.51
    Demografie
    -0.49
    Geplaatst
    -0.49
    AddHtmlAttribute
    -0.49
    POSITIVE LOGITS
     database
    1.23
     searchable
    1.17
     databases
    1.00
     Database
    0.94
    database
    0.88
    Database
    0.83
    searchable
    0.81
    数据库
    0.80
     indexing
    0.79
     DATABASE
    0.78
    Activations Density 0.771%

    No Known Activations