© 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. 12795
    Prev
    Next
    INDEX
    Explanations

    phrases related to initiating and managing tasks or projects

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

    the phrase "get" combined with action verbs or readiness states that indicate beginning or commencing an activity.

    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
     resourceCulture
    -0.34
    ranean
    -0.31
    GEBURTS
    -0.29
     azar
    -0.29
    inWeight
    -0.28
     Establishment
    -0.28
     frontières
    -0.28
     приез
    -0.28
    랜드
    -0.28
    الإنجليزية
    -0.28
    POSITIVE LOGITS
     igång
    0.72
     commenced
    0.69
     tackling
    0.68
    Sucesor
    0.68
     attacking
    0.67
     underway
    0.67
     busy
    0.66
     embarked
    0.65
     proceeding
    0.64
    さっそく
    0.62
    Activations Density 0.233%

    No Known Activations