© 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-2-9B
    7. Residual Stream - 16k
    9. 27-GEMMASCOPE-RES-16K
    11. 8512
    Prev
    Next
    INDEX
    Explanations

    terms related to technology products and services in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wireType
    -0.58
     mergeFrom
    -0.51
    évaluateur
    -0.49
     kasarigan
    -0.49
     utafitiHapana
    -0.49
    ↹
    -0.49
     intptr
    -0.48
    belea
    -0.44
    styleType
    -0.43
     Ongoing
    -0.43
    POSITIVE LOGITS
     primarily
    0.66
     principally
    0.66
     mainly
    0.65
    primarily
    0.64
     głównie
    0.63
     chiefly
    0.61
    mainly
    0.60
    主に
    0.59
    mostly
    0.57
     mostly
    0.56
    Activations Density 0.264%

    No Known Activations