© 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. 15728
    Prev
    Next
    INDEX
    Explanations

    references to personal experience or opinions

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

    first-person pronouns and their associated verbs expressing thoughts, beliefs, or observations.

    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
     however
    -1.01
    however
    -0.86
     però
    -0.84
     porém
    -0.81
     jedoch
    -0.81
     jednak
    -0.72
    However
    -0.71
     však
    -0.69
     However
    -0.68
     azonban
    -0.66
    POSITIVE LOGITS
     accordingly
    0.82
     correspondingly
    0.79
     consequently
    0.78
     consequent
    0.65
     therein
    0.63
     subsequently
    0.63
    脚注の使い方
    0.62
     therefore
    0.61
     autorytatywna
    0.60
    何より
    0.59
    Activations Density 0.347%

    No Known Activations