© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 8684
    Prev
    Next
    INDEX
    Explanations

    political commentary and critiques related to governance and economic policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    Related
    -0.31
     acordo
    -0.31
     sowas
    -0.30
     Related
    -0.30
     involucrados
    -0.30
     Trennung
    -0.30
     igreja
    -0.29
     Schriftsteller
    -0.29
     RELATED
    -0.28
     dalamnya
    -0.28
    POSITIVE LOGITS
    новништво
    0.74
    ATEGORIES
    0.62
     queſta
    0.59
    #+#
    0.59
     للمعارف
    0.58
    MLLoader
    0.57
    enderror
    0.57
    AndEndTag
    0.57
    MemoryWarning
    0.56
     kasarigan
    0.54
    Activations Density 0.188%

    No Known Activations