© 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. 1-GEMMASCOPE-RES-16K
    6. 2895
    Prev
    Next
    INDEX
    Explanations

    references to poetry and its various forms, as well as aspects of printing technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    =$?
    -0.43
    aktery
    -0.41
     صوتيه
    -0.40
     GenerationType
    -0.38
    RTGC
    -0.37
     باش
    -0.36
    Studios
    -0.36
    esModule
    -0.35
     studios
    -0.35
    defineProperty
    -0.35
    POSITIVE LOGITS
    PRINT
    0.81
    printing
    0.79
     Printing
    0.77
     printing
    0.76
    Printing
    0.74
    Print
    0.71
     planting
    0.69
    print
    0.69
    Printed
    0.65
     ſche
    0.65
    Activations Density 0.172%

    No Known Activations