© 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. 10789
    Prev
    Next
    INDEX
    Explanations

    specific references to decisions, their implications, and the context of acceptance within communities

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

    phrases expressing strong positive recommendations or endorsements, particularly around accepting decisions and embracing change.

    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
     propOrder
    -0.63
    brigens
    -0.59
    colgante
    -0.56
    ſſung
    -0.56
    ⏜
    -0.56
     geweſen
    -0.55
     zuſammen
    -0.54
     Dieſe
    -0.54
    <pad>
    -0.53
     $_-
    -0.53
    POSITIVE LOGITS
     rather
    3.95
     instead
    3.92
    instead
    3.50
    rather
    3.39
     plutôt
    3.16
    Instead
    3.13
     Rather
    3.11
     Instead
    3.09
     zamiast
    3.08
    Rather
    3.06
    Activations Density 2.624%

    No Known Activations