© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 12794
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty or conditions in scientific arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    transitional phrases and logical connectors that signal a contrast or conditional relationship between ideas.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    discourse connectives and transitional words that link ideas between clauses or sentences.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     незавершена
    -0.77
    enumii
    -0.68
     GenerationType
    -0.60
     CreateTagHelper
    -0.60
     nakalista
    -0.58
     defaultstate
    -0.57
    Tikang
    -0.56
    ViewImports
    -0.55
     فريبيس
    -0.55
    InjectMocks
    -0.54
    POSITIVE LOGITS
     considerable
    0.68
     použití
    0.68
     differences
    0.63
     différences
    0.62
     difficulties
    0.59
     dificultades
    0.57
     erheb
    0.57
     careful
    0.56
     diferencias
    0.56
     verschillen
    0.56
    Activations Density 1.955%

    No Known Activations