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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 482
    Prev
    Next
    INDEX
    Explanations

    concepts related to tattoo designs and their characteristics

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

    relating to style or design

    np_acts-logits-general · gemini-2.0-flash

    stylistic descriptions

    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
    QMetaType
    -0.54
    uestamente
    -0.52
     infrastruktur
    -0.52
     ſtate
    -0.50
     purpoſe
    -0.49
     procédures
    -0.48
     anſ
    -0.46
     deſt
    -0.46
     myſelf
    -0.46
     funzionamento
    -0.45
    POSITIVE LOGITS
     stylistic
    0.59
     styl
    0.59
     style
    0.59
     artistic
    0.57
     styles
    0.57
     aesthetic
    0.53
     gorgeous
    0.53
    ROIT
    0.52
     aesthetically
    0.51
     stijl
    0.50
    Activations Density 0.162%

    No Known Activations