Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 6577
    Prev
    Next
    INDEX
    Explanations

    quoted statements from individuals in authority or official positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    rungsseite
    -0.68
    
    -0.68
     الحره
    -0.64
    SharedDtor
    -0.60
    AndEndTag
    -0.60
     beginnetje
    -0.59
    StructEnd
    -0.59
    ViewFeatures
    -0.58
     AssemblyCompany
    -0.57
    fillType
    -0.56
    POSITIVE LOGITS
     officials
    0.48
     officers
    0.40
     Officials
    0.40
    Officials
    0.39
     Verwaltung
    0.38
     chiefs
    0.35
     oblic
    0.35
     officier
    0.35
     Tonnen
    0.35
    官员
    0.35
    Activations Density 0.388%

    No Known Activations