© 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. 4725
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences and interactions

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

    Second person pronouns followed by verbs

    np_acts-logits-general · gemini-2.0-flash

    you verb

    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
     a
    -0.29
    timeZone
    -0.25
    Werde
    -0.22
     صح
    -0.22
    Ethics
    -0.22
     ver
    -0.22
    Nazionale
    -0.21
    ц
    -0.20
     Ethics
    -0.20
    StoryboardSegue
    -0.20
    POSITIVE LOGITS
    хьтан
    0.71
    transQ
    0.71
     AssemblyTitle
    0.69
    styleType
    0.66
     chofe
    0.65
     uſed
    0.65
     مرئيه
    0.64
    RegressionTest
    0.63
    Portail
    0.62
     posted
    0.61
    Activations Density 0.265%

    No Known Activations