© 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-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 38558
    Prev
    Next
    INDEX
    Explanations

    special markers or headings that indicate the start of a new section or topic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]")]
    -0.95
    contentLoaded
    -0.84
     Curran
    -0.77
    Bans
    -0.74
    prc
    -0.73
    uolo
    -0.72
     Bans
    -0.71
    charCode
    -0.69
    Geplaatst
    -0.69
     bulat
    -0.68
    POSITIVE LOGITS
     IBM
    1.29
    ibm
    1.11
    IBM
    1.09
     Watson
    1.09
    Watson
    0.96
     WATSON
    0.94
     STM
    0.88
     Albert
    0.76
     Elephant
    0.74
    Elephant
    0.74
    Activations Density 0.034%

    No Known Activations