© 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-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 7083
    Prev
    Next
    INDEX
    Explanations

    references to celestial observations and their conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itudinal
    -0.48
    ftagPool
    -0.48
     incarnate
    -0.48
     acidosis
    -0.47
    ENCIA
    -0.47
     Kenji
    -0.45
     Byzantium
    -0.45
    GHIJKLM
    -0.45
    λισ
    -0.44
     مشين
    -0.44
    POSITIVE LOGITS
    <bos>
    0.69
     astronomer
    0.67
     astronomers
    0.66
    ⓧ
    0.66
    numerusform
    0.65
     astron
    0.65
     dAtA
    0.62
    GEBURTS
    0.62
    rxjs
    0.61
    WireFormatLite
    0.61
    Activations Density 0.297%

    No Known Activations