© 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. 4722
    Prev
    Next
    INDEX
    Explanations

    key questions and advice related to support and assistance for individuals and organizations

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

    offering assistance

    np_acts-logits-general · gemini-2.0-flash

    people needing help or facilitation

    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
    styleType
    -0.56
    MigrationBuilder
    -0.54
    ِّف
    -0.45
    Soorten
    -0.44
     OFDb
    -0.42
    държа
    -0.41
    TypedDataSet
    -0.41
    iserie
    -0.41
    verwijspagina
    -0.40
    FTAR
    -0.40
    POSITIVE LOGITS
     people
    0.96
     families
    0.78
     young
    0.71
     farmers
    0.71
     parents
    0.71
     individuals
    0.69
     seniors
    0.66
     persons
    0.65
     couples
    0.63
     folks
    0.63
    Activations Density 0.839%

    No Known Activations