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. 5-GEMMASCOPE-RES-16K
    6. 11173
    Prev
    Next
    INDEX
    Explanations

    terms related to justification and justification-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jLabel
    -0.78
    fcntl
    -0.71
    __((
    -0.69
    Xna
    -0.68
     незавершена
    -0.67
    ंदीखरीदारी
    -0.64
     teach
    -0.61
    πέ
    -0.61
    teaching
    -0.59
    ウェ
    -0.59
    POSITIVE LOGITS
     justified
    1.82
     justify
    1.75
     justifying
    1.74
     justifies
    1.73
    justify
    1.66
     Justification
    1.57
     justification
    1.56
     gius
    1.56
    Justification
    1.54
     Jus
    1.45
    Activations Density 0.121%

    No Known Activations