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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 9869
    Prev
    Next
    INDEX
    Explanations

    descriptive language that highlights aesthetic qualities and technical achievements in products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     الحره
    -0.80
    migrationBuilder
    -0.71
    تفصیلات
    -0.65
    UnknownFieldSet
    -0.58
    󠁢
    -0.56
    oltà
    -0.56
    ]--;
    -0.55
     protoimpl
    -0.54
     ModelExpression
    -0.53
    MessageTagHelper
    -0.53
    POSITIVE LOGITS
     aesthetically
    1.99
     aesthetics
    1.96
     aesthetic
    1.94
     beauty
    1.65
     Aesthetic
    1.63
    aesthetic
    1.62
     visually
    1.60
     Aesthetics
    1.60
    Aesthetic
    1.58
     estética
    1.56
    Activations Density 0.290%

    No Known Activations