© 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. 1073
    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
    printStackTrace
    -0.44
    urii
    -0.44
    ägg
    -0.44
     EClass
    -0.44
    pening
    -0.44
    AsUp
    -0.43
    klara
    -0.43
    Становништво
    -0.43
    anxi
    -0.41
     lode
    -0.40
    POSITIVE LOGITS
     ***!
    0.71
    setVerticalGroup
    0.67
     فريبيس
    0.63
     EconPapers
    0.60
     prefier
    0.60
    TestingModule
    0.59
     المعيارى
    0.59
     oprot
    0.58
    \{\\
    0.58
     estekak
    0.58
    Activations Density 0.220%

    No Known Activations