© 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. 56506
    Prev
    Next
    INDEX
    Explanations

    concepts related to gaps or voids in knowledge and understanding

    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
     AttributeSet
    -0.65
     ★★★★
    -0.50
    awaiter
    -0.49
     setae
    -0.49
     nucléaire
    -0.48
    LOYEES
    -0.48
     Leopold
    -0.48
    WebMethod
    -0.47
     nuclé
    -0.47
     genitori
    -0.46
    POSITIVE LOGITS
     gaps
    1.32
     gap
    1.27
     Gaps
    1.15
    gaps
    1.04
     Gap
    1.04
    gap
    0.95
    Gap
    0.90
     lacking
    0.85
     missing
    0.81
     fehlt
    0.80
    Activations Density 0.035%

    No Known Activations