© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 114557
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the inclusion or mention of 'some' type of specificity or subset

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

    some of the

    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
    IUrlHelper
    -0.38
    spricht
    -0.34
    endaten
    -0.33
     Anleitung
    -0.32
    SourceChecksum
    -0.32
    струкция
    -0.32
     çantası
    -0.32
     optimally
    -0.32
     dalamnya
    -0.31
    зонта
    -0.31
    POSITIVE LOGITS
     destacado
    0.54
     defaultstate
    0.52
    cipais
    0.51
    Среди
    0.51
     *++
    0.48
    餿
    0.48
     parmi
    0.48
    Aiheesta
    0.47
     Notable
    0.47
    heça
    0.47
    Activations Density 0.014%

    No Known Activations