© 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-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 8085
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of combining or blending elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 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
    GenerationType
    -0.57
    contentLoaded
    -0.53
    getChildAt
    -0.50
    adaptiveStyles
    -0.50
     NUKAT
    -0.50
    AccessorTable
    -0.48
     Bacteriol
    -0.48
    IsPostBack
    -0.47
    QMetaType
    -0.47
    VolleyError
    -0.47
    POSITIVE LOGITS
     combine
    3.42
     Combine
    3.20
     combining
    3.06
    combine
    2.95
     combines
    2.95
    Combine
    2.94
     Combining
    2.78
    Combining
    2.67
     combined
    2.64
     COMBIN
    2.48
    Activations Density 0.210%

    No Known Activations