© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 7651
    Prev
    Next
    INDEX
    Explanations

    expressions related to imagination or visualization

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

    "imagine" or its variants

    np_acts-logits-general · gemini-2.0-flash

    imagining events or scenarios

    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
     amitié
    -0.43
     évêque
    -0.40
     Wahrheit
    -0.40
     katholischen
    -0.40
     Universitaria
    -0.40
     Gerechtigkeit
    -0.39
     miłość
    -0.39
     igenom
    -0.39
     Überprüfung
    -0.39
     Erkenntnis
    -0.39
    POSITIVE LOGITS
     imagine
    1.59
     imagining
    1.58
     imagined
    1.57
    imagine
    1.52
     Imagine
    1.49
     imagines
    1.49
    Imagine
    1.45
     Imagin
    1.41
     imagin
    1.40
    Imagin
    1.37
    Activations Density 0.304%

    No Known Activations