© 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. 28-GEMMASCOPE-RES-16K
    11. 3906
    Prev
    Next
    INDEX
    Explanations

    connections between gene regulation and the effects on cellular behavior

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

    like "Interestingly", "Furthermore", or "suggesting"

    np_acts-logits-general · gemini-2.0-flash

    suggesting similarities

    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
     ***!
    -0.67
     GenerationType
    -0.49
     Offisielt
    -0.48
    aronder
    -0.47
    Біографія
    -0.46
    Sklici
    -0.45
     LoggerFactory
    -0.45
    存于互联网档案馆
    -0.45
    最快更新
    -0.44
     diagnose
    -0.44
    POSITIVE LOGITS
    Interestingly
    0.64
     similar
    0.62
    Similar
    0.60
     Similar
    0.58
     Interestingly
    0.57
    similar
    0.53
     similaire
    0.47
     suggesting
    0.46
    TagHelper
    0.45
     serupa
    0.45
    Activations Density 1.612%

    No Known Activations