© 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. 19-GEMMASCOPE-RES-16K
    11. 512
    Prev
    Next
    INDEX
    Explanations

    references to peaks in data distributions or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    er
    -0.74
    </strong>
    -0.63
    </h1>
    -0.62
    人
    -0.61
    
    -0.61
     Marcell
    -0.60
    PositiveButton
    -0.59
    BeforeEach
    -0.59
    mml
    -0.59
     Cosby
    -0.59
    POSITIVE LOGITS
    PerformLayout
    0.75
    存于互联网档案馆
    0.72
    SCRIBE
    0.70
    `{.
    0.69
    instorm
    0.69
     defaultstate
    0.66
    ))$.
    0.66
     AssemblyTitle
    0.66
    ].)
    0.65
     Twins
    0.64
    Activations Density 0.553%

    No Known Activations