© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 13-GEMMASCOPE-RES-16K
    11. 753
    Prev
    Next
    INDEX
    Explanations

    anatomical terms related to human figures and their positions within a hierarchy

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    fortawesome
    -0.48
    IMATE
    -0.44
     dimaksud
    -0.42
     aasta
    -0.42
    nivå
    -0.42
    åringen
    -0.42
    SHIRE
    -0.42
    といけない
    -0.41
     EventEmitter
    -0.40
    ന്ന
    -0.39
    POSITIVE LOGITS
     UNTIL
    0.68
     defaultstate
    0.68
    until
    0.66
    WithIOException
    0.65
    DockStyle
    0.65
     Италијани
    0.64
    certain
    0.64
     until
    0.64
     المعيارى
    0.63
     untill
    0.60
    Activations Density 0.573%

    No Known Activations