© 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-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 10844
    Prev
    Next
    INDEX
    Explanations

    elements related to food and dining experiences

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

    "...with a twist"

    np_acts-logits-general · gemini-2.0-flash

    adding a twist

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
    뀜
    -0.45
    HTTPResponse
    -0.44
    braio
    -0.43
     Provision
    -0.38
    赶
    -0.38
    Aiheesta
    -0.38
    hyd
    -0.38
     Katalog
    -0.38
    Histology
    -0.38
     Imports
    -0.37
    POSITIVE LOGITS
    principalColumn
    0.75
     twist
    0.56
     interpretation
    0.55
     reinterpret
    0.54
     NSCoder
    0.50
     twists
    0.49
     unconventional
    0.49
    Попис
    0.48
     clearColor
    0.48
    interpretation
    0.47
    Activations Density 0.449%

    No Known Activations