© 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. 15-GEMMASCOPE-RES-16K
    11. 3800
    Prev
    Next
    INDEX
    Explanations

    specific verbs related to declarations or announcements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ox
    -0.72
    didSet
    -0.58
     Mid
    -0.58
     far
    -0.56
     CanadaChoose
    -0.56
    imanapun
    -0.56
    Kno
    -0.54
    doge
    -0.53
    JNIEnv
    -0.52
    lotten
    -0.52
    POSITIVE LOGITS
     Declare
    1.40
     declares
    1.30
     declared
    1.30
     declaring
    1.30
     declare
    1.29
     declarations
    1.29
     declaration
    1.28
    eclared
    1.23
    Declare
    1.15
     Declaration
    1.09
    Activations Density 0.129%

    No Known Activations