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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 1098
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the use of evidence-based methods in research and decision-making

    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
    MigrationBuilder
    -1.35
    клопе
    -1.29
     '\\;'
    -1.28
    ^(@)
    -1.23
     يتيمه
    -1.21
    ########.
    -1.17
    DockStyle
    -1.12
    RectangleBorder
    -1.12
    verwijspagina
    -1.09
    bootstrapcdn
    -1.09
    POSITIVE LOGITS
     
    0.68
    ↵
    0.60
     also
    0.60
    :
    0.60
    ,
    0.58
    f
    0.58
    ↵↵
    0.55
     I
    0.55
    2
    0.55
     In
    0.54
    Activations Density 2.672%

    No Known Activations