© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 8154
    Prev
    Next
    INDEX
    Explanations

    discrepancies and variations in product representation and quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XmlAccessType
    -0.58
    Soorten
    -0.57
    UpInside
    -0.53
     ligiloj
    -0.51
    тература
    -0.50
    IVEREF
    -0.49
    principalTable
    -0.48
    [++
    -0.47
     analisi
    -0.47
     Eintritt
    -0.47
    POSITIVE LOGITS
    __]
    0.55
     Partager
    0.53
    warded
    0.53
    IndentedString
    0.52
     kaynağından
    0.52
     Majefty
    0.50
     ſch
    0.50
    ✭
    0.49
     ſche
    0.49
    ectl
    0.49
    Activations Density 0.046%

    No Known Activations