© 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. 14623
    Prev
    Next
    INDEX
    Explanations

    conjunctions and their frequency in the text

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

    the conjunction "and" used to connect list items or clauses.

    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
    小
    -0.52
    However
    -0.40
     However
    -0.37
    他
    -0.37
    她
    -0.36
    IBOutlet
    -0.36
     saja
    -0.35
    etheless
    -0.35
    平等
    -0.35
    >>>
    -0.35
    POSITIVE LOGITS
     hence
    0.88
     therefore
    0.84
     dermed
    0.83
     thus
    0.79
     consequently
    0.77
     somit
    0.74
    rogens
    0.71
    hence
    0.71
     subsequently
    0.68
     jednocześnie
    0.67
    Activations Density 1.385%

    No Known Activations