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-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 1074
    Prev
    Next
    INDEX
    Explanations

    references to sunlight and its impact on individuals or materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wiktionnaire
    -0.57
    msgTypes
    -0.55
    intios
    -0.53
     deflation
    -0.51
    PasswordField
    -0.51
     CreateTagHelper
    -0.51
     decorado
    -0.50
    Datuak
    -0.50
     voicing
    -0.50
     Emotion
    -0.50
    POSITIVE LOGITS
     sun
    2.40
     sunlight
    2.02
    sun
    1.98
     Sun
    1.88
     sunshine
    1.82
    Sun
    1.81
     SUN
    1.79
     Sunlight
    1.70
    Sunlight
    1.64
    SUN
    1.57
    Activations Density 0.198%

    No Known Activations