© 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. 15-GEMMASCOPE-RES-16K
    6. 2946
    Prev
    Next
    INDEX
    Explanations

    components related to database queries and data retrieval structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    database-related commands and operations within a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ReusableCell
    -0.87
     MainAxisSize
    -0.75
    AnchorStyles
    -0.70
     '\\;'
    -0.67
    RectangleBorder
    -0.66
     CascadeType
    -0.65
    UserScript
    -0.64
    WebpackPlugin
    -0.62
     مرئيه
    -0.62
    AxisAlignment
    -0.62
    POSITIVE LOGITS
    BASEPATH
    0.84
     Malaysia
    0.70
     Malaysian
    0.68
     Malay
    0.66
    Malaysia
    0.62
    AYSIA
    0.61
     malay
    0.60
     Malaya
    0.58
     durian
    0.58
     Singapore
    0.56
    Activations Density 0.013%

    No Known Activations