© 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. 11-GEMMASCOPE-RES-16K
    11. 8469
    Prev
    Next
    INDEX
    Explanations

    indicators of software bugs and related reporting details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/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.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     صوتيه
    -0.49
    存于互联网档案馆
    -0.46
    újo
    -0.46
     IBOutlet
    -0.45
    GOTREF
    -0.44
    MessageOf
    -0.43
    getDoctrine
    -0.42
     ioutil
    -0.42
    EndContext
    -0.42
    ModelSerializer
    -0.42
    POSITIVE LOGITS
     persoons
    0.44
     châssis
    0.42
    PreferredItem
    0.41
    ഔ
    0.39
    hite
    0.39
    NamedQueries
    0.39
     piemē
    0.39
    rel
    0.38
    org
    0.37
    Predecesor
    0.37
    Activations Density 0.576%

    No Known Activations