© 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. 7289
    Prev
    Next
    INDEX
    Explanations

    terms related to online gambling and casino promotions

    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
     TextAppearance
    -0.61
     ModelExpression
    -0.59
    UrlResolution
    -0.57
     كومونز
    -0.54
    AnchorTagHelper
    -0.52
    GOTREF
    -0.50
     älskar
    -0.48
    Hozzáférés
    -0.48
    fjspx
    -0.48
     سكانية
    -0.48
    POSITIVE LOGITS
     необ
    0.41
     OSC
    0.38
     Ox
    0.37
    strokeColor
    0.37
     FED
    0.35
     obfer
    0.35
     Zorn
    0.35
    Ox
    0.35
     FEM
    0.35
     Aubrey
    0.35
    Activations Density 0.019%

    No Known Activations