© 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 - 16k
    5. 12-GEMMASCOPE-RES-16K__L0-22
    6. 1009
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_22
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    r
    -0.91
    o
    -0.88
    n
    -0.80
    O
    -0.76
    b
    -0.76
    m
    -0.75
    l
    -0.72
    N
    -0.71
     devil
    -0.70
    P
    -0.70
    POSITIVE LOGITS
     itſelf
    1.23
     ་་
    1.17
     myſelf
    1.14
     Eſ
    1.09
     iſt
    1.07
    BibitemShut
    1.05
    leſs
    1.04
     themſelves
    1.03
     ―――――
    1.03
     Perſ
    1.02
    Activations Density 0.044%

    No Known Activations