© 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. 119755
    Prev
    Next
    INDEX
    Explanations

    the concept of independence across various contexts

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

    independent of external control

    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
     Meksi
    -0.51
    Beispiele
    -0.50
    endphp
    -0.50
     beliau
    -0.50
    achella
    -0.49
     iArr
    -0.48
    dialement
    -0.48
    tagext
    -0.47
    WireFormatLite
    -0.47
     Wikimedijinoj
    -0.47
    POSITIVE LOGITS
     independent
    2.09
    independent
    1.87
     Independent
    1.74
    Independent
    1.70
     INDEPENDENT
    1.60
     independently
    1.59
    独立
    1.49
     independence
    1.48
     independ
    1.47
     indépendante
    1.46
    Activations Density 0.017%

    No Known Activations