© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 4047
    Prev
    Next
    INDEX
    Explanations

    phrases related to benefits and improvements in overall experience or performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    didSet
    -0.48
    clearfix
    -0.47
    HomeAsUpEnabled
    -0.45
    khana
    -0.36
    inephrine
    -0.36
    ibat
    -0.36
     encontrarse
    -0.35
    HasAnnotation
    -0.34
    arro
    -0.34
    olol
    -0.34
    POSITIVE LOGITS
     NUKAT
    0.85
     يتيمه
    0.81
     SqlDbType
    0.77
    splat
    0.75
     Autorizaciones
    0.72
    Tikang
    0.72
     AssemblyProduct
    0.72
    ftagPool
    0.71
     Wicidata
    0.70
     LUMI
    0.70
    Activations Density 0.310%

    No Known Activations