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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 31260
    Prev
    Next
    INDEX
    Explanations

    phrases related to social and legal issues, particularly focusing on change and its implications

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

    temporal conjunctions and clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.81
    ConstraintMaker
    -0.74
     myſelf
    -0.67
     itſelf
    -0.63
     Monfieur
    -0.61
    ſelf
    -0.60
     Majefty
    -0.60
    ſelves
    -0.59
     Verſ
    -0.59
     ſtill
    -0.59
    POSITIVE LOGITS
    inguém
    0.38
     وتسجيلات
    0.38
     fallu
    0.37
     sfeer
    0.36
    atmosfera
    0.33
     stem
    0.33
    setViewportView
    0.32
     sorgen
    0.31
     intorno
    0.31
    gebnis
    0.31
    Activations Density 0.408%

    No Known Activations