© 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. 4060
    Prev
    Next
    INDEX
    Explanations

    negative aspects and limitations in various contexts

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

    contrastive statements introduced by "however" or similar transitional words that signal a shift from previous information.

    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
    الحياه
    -0.65
    }{%
    -0.56
    NameInMap
    -0.52
    adaptiveStyles
    -0.51
    Хьажоргаш
    -0.51
     الرياضيه
    -0.47
     незавершена
    -0.47
     &___
    -0.47
    Rohy
    -0.44
    ()][
    -0.44
    POSITIVE LOGITS
     however
    3.63
     però
    2.92
    however
    2.89
     cependant
    2.52
     porém
    2.47
     entanto
    2.41
     jedoch
    2.34
     toutefois
    2.31
    However
    2.31
     však
    2.30
    Activations Density 2.230%

    No Known Activations