© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 7995
    Prev
    Next
    INDEX
    Explanations

    references to blame and fault in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     quelcon
    -0.79
     représenté
    -0.79
    GOTREF
    -0.78
     EconPapers
    -0.77
    jsii
    -0.75
    ">//
    -0.74
     représ
    -0.74
     חיצוניים
    -0.73
     snippetHide
    -0.73
     ricev
    -0.73
    POSITIVE LOGITS
     fault
    3.49
     Fault
    2.91
    fault
    2.89
     faults
    2.59
    Fault
    2.53
    faults
    2.08
    FAULT
    2.05
    Faults
    1.81
     blame
    1.79
     faulting
    1.55
    Activations Density 0.099%

    No Known Activations