© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 11320
    Prev
    Next
    INDEX
    Explanations

    elements related to instructions or details in a technical or formal context

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

    website terms and conditions

    np_acts-logits-general · gemini-2.0-flash

    writing a letter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cielos
    -0.79
     dourada
    -0.69
    ohjel
    -0.65
    dotta
    -0.65
     auroit
    -0.60
     dioses
    -0.59
    OVERR
    -0.59
     boneca
    -0.58
     umana
    -0.57
     suun
    -0.57
    POSITIVE LOGITS
     eter
    0.56
     $_"
    0.53
     :",
    0.50
    Hozzáférés
    0.50
    principalTable
    0.49
    מבר
    0.48
    shortcuts
    0.48
     mola
    0.47
     anf
    0.47
     inder
    0.46
    Activations Density 0.429%

    No Known Activations