© 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. 9-GEMMASCOPE-RES-16K
    11. 2577
    Prev
    Next
    INDEX
    Explanations

    the presence of imperative phrases indicating actions or tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalTable
    -0.84
    XmlAccessorType
    -0.66
    RemoteException
    -0.66
    UnusedPrivate
    -0.66
    \"");
    -0.65
    sidemargin
    -0.64
    IsPostBack
    -0.64
    IUrlHelper
    -0.63
     beginnetje
    -0.62
    gonic
    -0.60
    POSITIVE LOGITS
    To
    1.10
     To
    1.06
     Чтобы
    0.85
    为了
    0.77
     Toh
    0.74
     Для
    0.73
    Для
    0.72
    Чтобы
    0.72
     Dazu
    0.70
     simplicity
    0.68
    Activations Density 0.145%

    No Known Activations