© 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. 4-GEMMASCOPE-RES-16K
    11. 11276
    Prev
    Next
    INDEX
    Explanations

    references to academic citations or research publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumi
    -0.54
     démocr
    -0.52
    ftagPool
    -0.50
    ल्क
    -0.48
    DRAM
    -0.47
     preuves
    -0.47
    льше
    -0.47
    jalá
    -0.46
    ➽
    -0.46
    efte
    -0.46
    POSITIVE LOGITS
     ModelExpression
    0.80
     الحره
    0.76
    UnsafeEnabled
    0.75
    XtraGrid
    0.64
    ISupport
    0.63
    GeneratedMessage
    0.63
    tagHelperRunner
    0.62
    DotNetBar
    0.61
     Wicidata
    0.61
    RoutingModule
    0.61
    Activations Density 0.260%

    No Known Activations