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

    Neuronpedia

    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
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 4238
    Prev
    Next
    INDEX
    Explanations

    phrases related to scientific experimentation and methodology

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

    Followed by a verb (can, will, is)

    np_acts-logits-general · gemini-2.0-flash

    gained, achieves, can

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     OnInit
    -0.44
     membutuhkan
    -0.44
     дописавши
    -0.43
     necesitar
    -0.42
    }()
    -0.40
    agaimana
    -0.39
     Мексичка
    -0.38
     gustan
    -0.38
     dėl
    -0.36
    }(),
    -0.36
    POSITIVE LOGITS
    就能
    0.60
     consegue
    0.59
     doká
    0.56
     gained
    0.56
     pysty
    0.56
     achieves
    0.54
    实现了
    0.54
    gain
    0.54
     rius
    0.53
    就可以
    0.53
    Activations Density 0.443%

    No Known Activations