© 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. 31-GEMMASCOPE-RES-16K
    11. 10744
    Prev
    Next
    INDEX
    Explanations

    expressions related to pursuing and achieving dreams

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

    dreams and aspirations, particularly when someone achieves or pursues their goals.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jsdelivr
    -0.43
    BagConstraints
    -0.41
     gawas
    -0.39
    ecuted
    -0.37
     toer
    -0.36
    leuth
    -0.36
    detectChanges
    -0.36
    bootstrapcdn
    -0.35
    ExecuteReader
    -0.35
     Ruhe
    -0.34
    POSITIVE LOGITS
     dream
    2.83
     dreams
    2.75
    dream
    2.34
     dreaming
    2.27
    dreams
    2.23
     dreamed
    2.20
     Dreams
    2.19
     DREAM
    2.17
     Dream
    2.13
    Dream
    2.09
    Activations Density 0.459%

    No Known Activations