© 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. 28-GEMMASCOPE-RES-16K
    6. 3587
    Prev
    Next
    INDEX
    Explanations

    items related to bags and their characteristics

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

    Something being filled, contained, or occupied

    np_acts-logits-general · gemini-2.0-flash

    filled with

    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
    providedIn
    -0.44
    ngdoc
    -0.38
    BeginContext
    -0.37
     विश्वसनीयता
    -0.37
    IInterface
    -0.37
    liceerd
    -0.34
    SPJ
    -0.34
    тія
    -0.34
    IndentedString
    -0.33
    Климат
    -0.33
    POSITIVE LOGITS
     containing
    1.30
     filled
    1.27
     Filled
    1.13
     contain
    1.09
     Containing
    1.08
     diisi
    1.06
     contenant
    1.05
     contains
    1.04
    Filled
    1.03
    containing
    1.02
    Activations Density 0.998%

    No Known Activations