© 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. 3-GEMMASCOPE-RES-16K
    11. 10418
    Prev
    Next
    INDEX
    Explanations

    programming language keywords and constructs related to functions and error handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.73
     '>=
    -0.67
     !!}
    -0.62
     JpaRepository
    -0.62
     Dage
    -0.61
    хьтан
    -0.60
    })$}
    -0.60
    ContentAlignment
    -0.59
    DrawerToggle
    -0.59
    esistenza
    -0.58
    POSITIVE LOGITS
     bParam
    0.82
     r
    0.81
    r
    0.64
     defer
    0.57
    ISupport
    0.56
     OnInit
    0.55
    าสตร์
    0.53
    følgelig
    0.51
    addComponent
    0.49
    rzost
    0.49
    Activations Density 0.039%

    No Known Activations