© 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. 3658
    Prev
    Next
    INDEX
    Explanations

    references to data storage and usage-related terminology

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

    Tokens followed by "there"

    np_acts-logits-general · gemini-2.0-flash

    locations and places

    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
    \{\\
    -0.47
     FetchType
    -0.45
    scalatest
    -0.42
     calendriers
    -0.40
    CloseOperation
    -0.40
     StringTokenizer
    -0.39
    .*")]
    -0.38
     cocción
    -0.38
    RectangleBorder
    -0.38
    fromnode
    -0.37
    POSITIVE LOGITS
     там
    1.86
     allí
    1.83
     therein
    1.80
     dort
    1.70
    在那里
    1.65
     آنجا
    1.59
     thither
    1.57
    Там
    1.48
     here
    1.46
    那里
    1.45
    Activations Density 1.195%

    No Known Activations