© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 3685
    Prev
    Next
    INDEX
    Explanations

    information related to representation and diversity in media

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

    Preceding numbers

    np_acts-logits-general · gemini-2.0-flash

    movie and film

    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
     zákaz
    -0.42
    protoimpl
    -0.41
    PerformLayout
    -0.39
     assistência
    -0.38
     fotografico
    -0.35
     estudante
    -0.35
    这个人
    -0.35
     témoignage
    -0.34
    setupUi
    -0.34
     ilustracji
    -0.34
    POSITIVE LOGITS
     movie
    1.27
     film
    1.15
     movies
    1.06
    movie
    1.05
     films
    1.02
    film
    0.99
    Movie
    0.97
     Movie
    0.94
    movies
    0.91
    Film
    0.90
    Activations Density 0.293%

    No Known Activations