© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 3026
    Prev
    Next
    INDEX
    Explanations

    terms related to the construction and setup of dialog boxes in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Builder"

    np_acts-logits-general · gemini-2.0-flash

    builder pattern in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tikang
    -0.50
     esternos
    -0.48
    Referències
    -0.39
    Océ
    -0.38
     Gegend
    -0.37
     quæ
    -0.37
    näm
    -0.37
    Rujukan
    -0.36
    Non
    -0.36
    principalColumn
    -0.35
    POSITIVE LOGITS
    Builder
    3.27
    builder
    2.98
     Builder
    2.95
     builder
    2.91
     builders
    2.55
    builders
    2.33
     Builders
    2.31
    Builders
    2.19
     BUILD
    1.77
    newBuilder
    1.54
    Activations Density 0.052%

    No Known Activations