Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 80839
    Prev
    Next
    INDEX
    Explanations

    references to the concept of dreams and aspirations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     informaciones
    -0.45
    ubby
    -0.42
     carreteras
    -0.42
     Sixers
    -0.41
     personen
    -0.41
     naciones
    -0.40
    gesellschaft
    -0.40
    ulele
    -0.40
     sociedades
    -0.40
     personnes
    -0.40
    POSITIVE LOGITS
    Dream
    1.15
     DREAM
    1.14
     dream
    1.14
     Dream
    1.13
    DREAM
    1.11
    dream
    1.10
     dreams
    1.04
     dreamed
    0.96
    Dreams
    0.96
     Dreams
    0.94
    Activations Density 0.003%

    No Known Activations