© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 12693
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to characters and events in entertainment and sports contexts

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

    proper nouns and character/place names from fictional works.

    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
    0
    -0.35
    1
    -0.34
    it
    -0.34
    i
    -0.33
    3
    -0.33
    2
    -0.33
     van
    -0.32
    if
    -0.31
    p
    -0.29
    k
    -0.29
    POSITIVE LOGITS
    iſen
    1.02
    ſcher
    1.00
    
    0.94
    mpagne
    0.93
    WriteTagHelper
    0.93
     invokingState
    0.92
     snippetHide
    0.92
    ikusbot
    0.91
    iſten
    0.91
    majánló
    0.90
    Activations Density 2.943%

    No Known Activations