© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 8680
    Prev
    Next
    INDEX
    Explanations

    phrases related to quality assessments and the concept of being "good" or "better."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     perfect
    -0.59
     élégant
    -0.54
     perfeito
    -0.52
    declare
    -0.52
    artifactId
    -0.52
     heerlijk
    -0.51
    Perfect
    -0.50
     bonne
    -0.50
    Assista
    -0.50
     good
    -0.50
    POSITIVE LOGITS
     deal
    0.83
    CppMethod
    0.73
     deals
    0.73
     behaved
    0.72
     defaultstate
    0.69
    ulously
    0.69
    SourceChecksum
    0.69
     value
    0.67
     idea
    0.66
     smelling
    0.66
    Activations Density 0.214%

    No Known Activations