© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 12215
    Prev
    Next
    INDEX
    Explanations

    expressions related to making choices or preferences

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

    non-English language text and characters, particularly from Arabic, Southeast Asian languages, and other non-Latin scripts.

    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
     ujednoznacz
    -0.69
     auroit
    -0.65
    ſſung
    -0.64
    niſſe
    -0.64
    saraba
    -0.63
    AddTagHelper
    -0.63
    iſche
    -0.62
    iſchen
    -0.61
     témoig
    -0.61
     pouvoit
    -0.60
    POSITIVE LOGITS
    NSArray
    0.35
    いえば
    0.35
     viață
    0.33
    enschappelijke
    0.32
    úrate
    0.31
     Serikat
    0.30
    doise
    0.30
     ActiveRecord
    0.29
     fame
    0.29
     Linie
    0.29
    Activations Density 0.013%

    No Known Activations