© 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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 105683
    Prev
    Next
    INDEX
    Explanations

    references to companies and their market actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     ujednoznacz
    -0.75
    OGND
    -0.72
    jsii
    -0.66
    SourceChecksum
    -0.65
     wikipagina
    -0.63
    HomeAsUpEnabled
    -0.63
    IonicModule
    -0.61
    SBATCH
    -0.60
    TemporalType
    -0.59
    ыгана
    -0.59
    POSITIVE LOGITS
    ilever
    0.61
     Unilever
    0.55
     Brands
    0.47
     Nestlé
    0.46
     createSprite
    0.42
     manufacturer
    0.41
     marketer
    0.41
     Nestle
    0.41
     Coca
    0.39
     product
    0.39
    Activations Density 0.018%

    No Known Activations