© 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. 12-GEMMASCOPE-RES-16K
    6. 4753
    Prev
    Next
    INDEX
    Explanations

    technical specifications and references in diagrams or code-related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.51
    Regressor
    -0.47
    bcryptjs
    -0.44
    PickerController
    -0.44
    momix
    -0.43
    WebVitals
    -0.42
    RectangleBorder
    -0.40
     ffilm
    -0.39
     Parame
    -0.39
    GroupLayout
    -0.39
    POSITIVE LOGITS
    private
    0.71
    FXML
    0.63
    IBOutlet
    0.61
     IBOutlet
    0.59
     private
    0.57
    endregion
    0.57
    setupUi
    0.57
    BindView
    0.56
     hObject
    0.53
    Private
    0.53
    Activations Density 0.160%

    No Known Activations