© 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. 0-GEMMASCOPE-RES-16K
    11. 8238
    Prev
    Next
    INDEX
    Explanations

    phrases related to the action of filling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BASEPATH
    -0.57
    YMMV
    -0.55
    ReusableCell
    -0.53
    styleUrls
    -0.52
     marbre
    -0.51
    ixas
    -0.50
    равда
    -0.50
     tế
    -0.50
    posables
    -0.49
    remoto
    -0.49
    POSITIVE LOGITS
     Fill
    1.53
     fill
    1.50
     filling
    1.50
    Fill
    1.46
     Filling
    1.43
     FILL
    1.43
    filling
    1.36
    Filling
    1.35
    fill
    1.32
     fills
    1.29
    Activations Density 0.125%

    No Known Activations