© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 7172
    Prev
    Next
    INDEX
    Explanations

    discussions around justification and rationalization in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    footer
    -0.59
    peč
    -0.58
     residue
    -0.56
     Bielefeld
    -0.54
    Footer
    -0.51
     urea
    -0.51
     Mecklenburg
    -0.51
     Chantal
    -0.50
    Familien
    -0.50
     présidenti
    -0.49
    POSITIVE LOGITS
     justify
    2.28
     justified
    2.13
     justifies
    1.98
     justification
    1.95
     justifying
    1.94
    justify
    1.77
     Justification
    1.70
    justified
    1.68
     gius
    1.64
    Justification
    1.64
    Activations Density 0.070%

    No Known Activations