© 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. 30-GEMMASCOPE-RES-16K
    11. 10686
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the presence of specific content or data

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

    Sentences using the word "contains" or "containing"

    np_acts-logits-general · gemini-2.0-flash

    contains [quantity/elements]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    يميديا
    -0.57
    RegressionTest
    -0.50
    bootstrapcdn
    -0.49
    #+#
    -0.48
     démocr
    -0.47
     pleaſure
    -0.47
     desmotivaciones
    -0.47
    AnimationsModule
    -0.47
    Guerra
    -0.47
     Perſ
    -0.46
    POSITIVE LOGITS
     mostly
    0.58
     contains
    0.57
     many
    0.57
     Contains
    0.56
    contains
    0.56
     elements
    0.54
    mostly
    0.50
     contém
    0.50
     contain
    0.49
    が含ま
    0.49
    Activations Density 0.464%

    No Known Activations