© 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. 28-GEMMASCOPE-RES-16K
    11. 6913
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names related to specific entities or organizations

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

    starting with "K" followed by two more letters

    np_acts-logits-general · gemini-2.0-flash

    K-prefixed names and technical terms

    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
    msgTypes
    -0.44
    weetie
    -0.43
    XmlAccessType
    -0.43
    Erica
    -0.42
    AUF
    -0.42
    Dear
    -0.40
    Compound
    -0.40
    Swe
    -0.40
     Swe
    -0.40
    bruik
    -0.38
    POSITIVE LOGITS
     IndexPath
    0.45
    webElementGuid
    0.45
     snippetHide
    0.45
     Kab
    0.44
     wireType
    0.44
    CORBA
    0.43
     Kar
    0.42
     producenta
    0.42
     ſich
    0.42
    Slf
    0.42
    Activations Density 0.178%

    No Known Activations